cs.NI — Pith

0

cs.AI 2026-07-03

Criticality checks validate AI decisions before telecom network changes

by Ravi Kant Sharma

Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Networks

A runtime framework scores decisions on multiple dimensions and applies graduated checks to prevent errors in autonomous networks.

abstract click to expand

The evolution toward fully autonomous telecommunications networks (Autonomous Network Levels 4-5) requires AI/ML agents to make real-time network decisions without human intervention. However, no standardized runtime mechanism exists to intercept and validate individual inference outputs before they trigger live network state changes, creating risks of erroneous autonomous decisions. This paper proposes the Guard Rail Validation (GRV) framework, a standardizable runtime architecture for intercepting and validating AI-driven decisions before execution. The framework evaluates decisions across multiple weighted dimensions -- including action scope, action type, service criticality, agent autonomy level, reversibility, and temporal behavioural patterns -- to determine a criticality level. Based on this level, graduated validation mechanisms are applied: execute-with-logging, bounds checking, independent agent validation, or multi-agent consensus. The framework additionally provides cross-agent conflict detection with criticality-weighted priority resolution and runtime conformance logging for regulatory compliance (e.g., EU AI Act Article 14). We present the architecture, algorithmic procedures, O-RAN deployment model, and evaluate threat coverage against known AI/ML attacks in telecommunications.

0

cs.NI 2026-07-03

Gain control makes additive noise fail for CSI simulation

by Aymen Bouferroum (FUN), Ildi Alla (uni.lu) +2 more

CSI Simulation: Why Additive Noise Fails and How to Fix It

M_QTC learns the multiplicative amplitude mapping from measurements and lets classifiers recover 93% of real jamming detection performance.

abstract click to expand

Channel State Information (CSI) has become a widely used wireless channel sensing modality for applications such as indoor localization, activity recognition, and respiration monitoring. Because collecting labeled data under every target condition is impractical, training CSI-based models often relies on simulated data produced by adding noise or perturbations to recorded channel estimates, most commonly additive white Gaussian noise (AWGN). This practice assumes that the receiver chain between the antenna and the channel estimator is linear and gain-invariant. We test this assumption empirically using RF jamming as a controlled perturbation on 6 commodity receivers across 2 indoor environments. The assumption does not hold. Automatic gain control compresses the channel estimate multiplicatively before digitization, producing amplitude distributions that no additive noise variance can reproduce. To close the resulting fidelity gap, we propose M_QTC, a measurement-calibrated model that learns the per-subcarrier distribution transformation through quantile mapping, temporal filtering, and copula-based cross-subcarrier reordering. M_QTC reduces amplitude error 8-fold and closes 89% of the aggregate fidelity gap across four complementary dimensions. The improvement transfers directly to downstream tasks, where 5 classifiers from different families trained on M_QTC-simulated data recover 93% of real-data jamming detection performance, while AWGN-trained classifiers remain near random decision.

0

cs.NI 2026-07-03

Lightweight AI runs in microseconds inside O-RAN Near-RT RIC xApp

by Lawrence Obiuwevwi, Krzysztof J. Rechowicz +8 more

Enabling Real-Time AI in O-RAN: Deploying andMeasuring AI Inside a Near-RT RIC xApp

Logistic regression and MLP models stay under 4 ms end-to-end while satisfying the 10 ms timing constraint on OAI/FlexRIC testbed.

abstract click to expand

Open Radio Access Network (O-RAN) architectures introduce programmable Near-Real-Time RAN Intelligent Controllers (Near-RT RICs) that support closed-loop control through xApps at timescales from 10 ms to 1 s. Although AI has been widely studied for RAN optimization, fewer works demonstrate measured AI inference embedded directly within the Near-RT RIC software loop on a live testbed. This paper presents an AI-enabled network-state classification xApp implemented on an OpenAirInterface (OAI) and FlexRIC testbed. The xApp is trained and evaluated on a structured synthetic dataset that emulates cross-layer RAN states using MAC, RLC, PDCP, GTP, and UE-count features. The results validate embedding and execution feasibility rather than production-level generalization. Logistic regression and a shallow multilayer perceptron (MLP) are exported as deterministic C inference modules and compiled into the xApp binary, eliminating external machine-learning runtime dependencies. Measured inference latency is 1 to 5 microseconds for logistic regression and 10 to 25 microseconds for the MLP, while end-to-end service latency remains below 4 ms. A six-model comparison shows that supervised models achieve similar accuracy, ranging from 0.88 to 0.90, indicating that LR and MLP similarity reflects the proxy problem structure rather than limited model exploration. Noise ablation, confusion-matrix analysis, and CDF-based latency characterization show that both embedded models satisfy the 10 ms Near-RT budget for more than 95% of projected loop executions. These results demonstrate that lightweight AI can operate within Near-RT RIC timing constraints while preserving deterministic execution. We also release RIC Workbench, a lightweight orchestration dashboard for reproducing the testbed on commodity hardware.

0

cs.NI 2026-07-02

Unsupervised detector ranks all trawler contacts on subsea cable

by Agastya Raj, Alvaro Doval +3 more

Fully Unsupervised Detection of Physical Contacts on Subsea Cables via State-of-Polarization Monitoring

Polarization data from a live cable lets a label-free model surface every confirmed contact in the top 13 of 122k recordings.

abstract click to expand

We present a fully unsupervised Fast-Slow DSVDD detector for continuous State-of-Polarization monitoring on a deployed subsea cable. Trained without event labels, it ranks all five confirmed trawler contacts within the top 13 of 122,174 recordings and surfaces additional corroborated cable-contact events.

0

cs.RO 2026-07-02

ROS 2 middleware faces trade-offs in space

by Sanghoon Lee, Taehun Kim +2 more

The Three Dimensions of ROS 2 Middleware

Spatial abstraction hides network issues while state continuity adds overhead that competes with control timing in wireless settings.

abstract click to expand

ROS 2 (Robot Operating System 2) has emerged as the de facto standard for modern robot software development, with middleware implementations such as the Data Distribution Service (DDS) and Zenoh forming the core infrastructure for distributed robotic communication. Despite their architectural flexibility, these middleware systems exhibit structural limitations, particularly under dynamic and resource-constrained wireless environments. This paper presents a systematic survey of ROS 2 middleware and introduces a conceptual framework to examine its architectural limits through three structural dimensions required by distributed robotic systems, namely Space, Time, and State. We first provide a structured analysis of middleware architecture and operational dynamics, including discovery, data exchange, and state management mechanisms. Building on this foundation, we formalize Time as temporal predictability for control loops, Space as spatial abstraction from physical topology to enable modular deployment, and State as contextual continuity despite dynamic node participation and intermittent connectivity. Through a comprehensive review of existing implementations and prior studies, we organize middleware research according to the structural trade-offs that arise among these dimensions. Under constrained wireless conditions, spatial abstraction can obscure network variability and weaken temporal guarantees, while mechanisms that preserve state continuity introduce computational and network overhead that competes with time-critical communication. These interactions reveal structural trade-offs that characterize the practical limits of contemporary robot middleware. By synthesizing architectural patterns and identifying gaps in current modeling and analysis approaches, this survey outlines a principled research roadmap for robust and scalable robotic middleware architectures.

0

cs.NI 2026-07-02

Data balancing cuts adaptation time 37% in optical attack detection

by Aleksandra Knapińska, Marija Furdek

Data-driven mitigation of catastrophic forgetting in dynamic physical layer attack detection

Retaining past attack samples in update batches lets models handle new threats without losing detection of old ones on experimental datasets

abstract click to expand

Optical networks are critical infrastructure that underpins global communications, and detecting security breaches that jeopardize them is essential to maintaining worldwide connectivity. As malicious actors continuously evolve their attack techniques, dynamically updated intrusion detection models have become a key component of modern defense mechanisms. By incorporating newly acquired telemetry data, these models can adapt to emerging threats while maintaining high detection performance. However, when previously encountered attacks reappear after a prolonged period of absence, adaptive models may fail to recognize them due to the phenomenon of catastrophic forgetting. In contrast, statically trained models can reliably detect attacks represented in the original training data but lack the ability to adapt to previously unseen attack patterns. Consequently, intrusion detection systems face a fundamental tradeoff between adaptability to evolving threats and long-term retention of previously acquired knowledge. In this work, we propose a data-driven mechanism to cope with catastrophic forgetting in dynamic attack detection systems. Our approach balances the model update datasets by using parts of past attack data. We utilize a threshold-based mechanism to trigger data balancing after accuracy drops due to an active attack change. Applied to an experimental optical network security dataset, the proposed approach reduces the average model adaptation time by 37% compared to its dynamic counterpart that does not employ data balancing. Compared to a baseline from the literature that relies on neural network depth increasing, our approach requires 6% fewer data batches to adapt to changing conditions and regain performance.

0

cs.NI 2026-07-02

Closed-form threshold minimizes total sensing error

by Sushila Dhaka, Jane-Hwa Huang +2 more

SNR-Adaptive Optimal Threshold Design for Energy Detection in Dynamic Spectrum Access

Quadratic expression in SNR and sample count yields an adaptive threshold that lowers overall error versus fixed or CFAR schemes.

abstract click to expand

This paper proposes an SNR-adaptive optimal threshold design framework for energy detection in Dynamic Spectrum Access (DSA). Unlike conventional constant false-alarm rate (CFAR)-based schemes that determine the sensing threshold solely from a predefined false-alarm constraint, the proposed method directly minimizes the total probability of error by deriving a closed-form analytical solution. The threshold optimization problem is formulated as a quadratic expression whose coefficients explicitly characterize the effects of signal-to-noise ratio (SNR) and number of samples. This analytical structure enables adaptive threshold selection under heterogeneous SNR conditions without exhaustive numerical search. Simulation results demonstrate that the proposed approach reduces the error probability compared with fixed-threshold and detection-constrained schemes, particularly in low-SNR regimes. Furthermore, the impact of SNR and number of samples on detection performance is systematically analyzed, providing deeper insight into the trade-off between false alarm and missed detection. The proposed framework improves sensing reliability and practical adaptability in dynamic spectrum access systems. It also establishes a foundation for secure cooperative spectrum sensing, including blockchain-assisted aggregation mechanisms.

0

cs.NI 2026-07-02

15% radio samples yield cuboid obstacle models for port base stations

by Paulo Furtado Correia, André Coelho +1 more

Mobile Base Station Positioning in Smart Ports Based on Kriged Sparse Measurements and Obstacle Inference

DOCKING reconstructs REMs via kriging, infers compact blockages, and optimizes MIAB placement to reach 150% capacity gains without geometry

abstract click to expand

Smart-port wireless networks suffer from dynamic radio blockage caused by container stacks and industrial structures, challenging efficient mobile integrated access and backhaul (MIAB) deployment. Existing approaches rely on obstacle maps, geometry information, or computationally intensive propagation models that limit adaptability. This paper presents DOCKING, a radio environment map (REM)-driven framework that converts sparse radio measurements into optimization-ready obstacle representations for MIAB deployment. The framework infers propagation-relevant obstacle abstractions from reconstructed REMs, eliminating the need for obstacle-geometry databases while relying only on known network parameters and sparse measurements. Reference signal received power (RSRP) and signal-to-interference-plus-noise ratio (SINR) observations are reconstructed using Ordinary Kriging (OKG), and dominant attenuation regions are approximated by compact cuboidal blockage models. The inferred geometry feeds a backhaul-aware optimization that determines MIAB placement, user equipment (UE) association, and backhaul selection. Under realistic smart-port conditions, REM reconstruction achieves prediction errors below 3 dB at the 90th percentile using only 15% spatial sampling, while obstacle characterization exceeds 85% true-positive coverage. Capacity gains reach 150% in sparse deployments, and a fast Genetic Algorithm converges within 5-15 s per network snapshot. A field campaign using real measurements validates the workflow, showing throughput trends consistent with optimization predictions. Results demonstrate that sparse radio measurements provide sufficient environmental awareness for practical obstacle-aware MIAB deployment in obstruction-prone industrial environments.

0

cs.NI 2026-07-02

5G RAN slicing meets rate and latency demands for mixed traffic

by Jan García-Morales, M. Carmen Lucas-Estañ +1 more

Latency-Sensitive 5G RAN Slicing for Industry 4.0

Schemes design slices and allocate resources to support deterministic and nondeterministic applications simultaneously.

abstract click to expand

Network slicing is a novel 5G paradigm that exploits the virtualization and softwarization of networks to create different logical network instances over a common network infrastructure. Each instance is tailored for specific Quality of Service (QoS) profiles so that network slicing can simultaneously support several services with diverse requirements. Network slicing can be applied at the Core Network or at the Radio Access Network (RAN). RAN slicing is particularly relevant to support latency-sensitive or timecritical applications since the RAN accounts for a significant part of the end-to-end transmission latency. In this context, this study proposes a novel latency-sensitive 5G RAN slicing solution. The proposal includes schemes to design slices and partition (or allocate) radio resources among slices. These schemes are designed with the objective to satisfy both the rate and latency demands of diverse applications. In particular, this study considers applications with deterministic aperiodic, deterministic periodic and nondeterministic traffic. The latency-sensitive 5G RAN slicing proposal is evaluated in Industry 4.0 scenarios where stringent and/or deterministic latency requirements are common. However, it can be evolved to support other verticals with latency-sensitive or time-critical applications.

0

cs.NI 2026-07-02

Linear programming assigns RAT and resources to meet QoS

by M.Carmen Lucas-Estañ, Javier Gozalvez +1 more

Common Radio Resource Management Policy for Multimedia Traffic in Beyond 3G Heterogeneous Wireless Systems

A common radio resource management policy uses linear functions to select technology and allocate resources in beyond 3G systems.

abstract click to expand

Beyond 3G wireless systems will be composed of a variety of Radio Access Technologies (RATs) with different, but also complementary, performance and technical characteristics. To exploit such diversity while guaranteeing the interoperability and efficient management of the different RATs, common radio resource management (CRRM) techniques need to be defined. This work proposes and evaluates a CRRM policy that simultaneously assigns to each user an adequate combination of RAT and number of radio resources within such RAT to guarantee its QoS requirements. The proposed CRRM technique is based on linear objective functions and programming tools.

0

cs.NI 2026-07-02

Configured Grant boosts number of supported TSN flows in 5G

by Ana Larrañaga, M. Carmen Lucas-Estañ +2 more

5G Configured Grant Scheduling for 5G-TSN Integration for the Support of Industry 4.0

Coordination with TSN information allows more deterministic flows to meet their end-to-end latency requirements.

abstract click to expand

Factories are evolving towards digitalized data-based ecosystems under the paradigm of the Industry 4.0 where new industrial services allow the implementation of more robust, resilient and customized manufacturing systems. Such services (e.g., digital twins, extended reality or cooperative robots) will require highly reliable and deterministic communication networks capable of supporting stringent latency and reliability requirements. 5G networks and their future evolution have the necessary capabilities to meet these requirements. However, the use of 5G in industrial environments requires its effective and efficient integration with Time Sensitive Networking (TSN), which is becoming the standard wired technology for Industry 4.0 environments. TSN provides unprecedented deterministic service levels with perfectly bounded latencies. The integration of the industrial 5G and TSN networks will be key to support the flexibility and determinism demanded by the Industry 4.0 paradigm. A critical aspect to achieve this integration is the coordination of the schedulers of both networks. TSN has information about the capabilities of the 5G-TSN integrated network, and it is in charge of deciding the path and scheduling for each TSN traffic flow. The scheduling in 5G must be done according to the scheduling decisions and information provided by TSN to guarantee the end-to-end latency requirements of TSN traffic. In this context, this paper proposes a novel Configured Grant scheduling scheme for 5G integrated into a TSN network that aims to meet the latency requirements of the different TSN flows. The proposed scheme exploits the information provided by TSN about the characteristics of the TSN traffic to coordinate its decision with the scheduling of TSN. This study demonstrates that the proposed scheduling scheme considerably increases the number of TSN flows that can be satisfactorily served.

0

cs.NI 2026-07-02

Scalar potential field governs load evolution in moving networks

by Wen-Yu Dong, Weiwei Jiang +3 more

Fluid-Spatiotemporal Stochastic Geometry: Information Flow in Non-Stationary Fields

Optimal transport yields existence and uniqueness for compressive dynamics under hydrodynamic topology limit

abstract click to expand

The fundamental limits of information flow in spatial networks are usually characterized under stationary spatial point processes, but this assumption cannot capture non-stationary regimes where the node intensity field evolves continuously in space and time. This paper develops Fluid-Spatiotemporal Stochastic Geometry (F-STSG), treating dynamic network topology as a hydrodynamic limit of the discrete node constellation. We formulate the identification of latent network dynamics as an inverse boundary value problem and, using the minimum kinetic energy principle from optimal transport, establish the existence and uniqueness of a scalar potential field governing the compressive evolution of network load. The resulting field-theoretic formulation couples continuous Lagrangian transport with discrete Eulerian interference geometry. Based on this model, we derive the information flux vector as a sufficient statistic for macroscopic advection and the material derivative as a kinematic predictor of topological divergence. We further characterize non-stationary network limits through energy-density scaling and source-channel interpretation, showing how coordination overhead, topology deformation, and control signaling requirements are linked to the kinematic entropy of the evolving network topology.

0

cs.NI 2026-07-02

Non-technical barriers limit vehicle-to-grid rollout more than tech

by Shangqing Wang, Laura del Rio Carazo +1 more

Vehicle-to-Grid as a 5G Smart Grid Vertical: Non-Technical Barriers and Implications for Communication Networks

Review of 974 studies shows 5G V2G design must incorporate business, policy and social constraints from the start.

abstract click to expand

Vehicle-to-Grid (V2G) and broader Vehicle-to-Everything (V2X) technologies are technically mature and widely demonstrated, yet large-scale deployment is constrained mainly by non-technical rather than communication or power-electronics limits. This paper targets the wireless communications community and frames V2G as a 5G-enabled smart grid vertical, linking business, governance, social, and infrastructure barriers to concrete communication-system requirements. Building on a PRISMA-guided systematic review of 974 V2G/V2X publications (2009-2025), and 162 implementation-critical studies, we adopt a four-domain framework of non-technical barriers: Business/Economic, Governance/Policy, Social, and Infrastructure/Ecosystem. Temporal and regional analyses show a shift from technical dominance to multidisciplinary integration after 2021. We translate these domains into communication requirements for V2G verticals, including fine-grained metering and settlement, protocol interoperability (e.g., ISO~15118, OCPP), privacy-by-design data governance, latency- and reliability-differentiated services, and edge-cloud partitioning for flexibility control. The results demonstrate that 5G design for V2G cannot be a purely technical optimization task and must integrate socio-technical constraints from the outset, suggesting research directions for sustainable, data-driven V2G communication architectures.

0

cs.NI 2026-07-02

Bayesian optimization delivers 72.8% farm coverage with 3 base stations

by Gourav Prateek Sharma, Durgesh Singh +1 more

Robust Base Station Placement in Agricultural IoT via Bayesian Optimization

Uses under 50 ray-tracing simulations to beat other methods by 4.6 points across crop seasons.

abstract click to expand

Precision-agriculture networks based on private 5G NR should ensure reliable connectivity for IoT sensor nodes throughout the crop growing season, yet the propagation environment changes dramatically as vegetation grows and matures. We formulate $K$-base-station~(BS) placement as a \textit{maximin seasonal coverage} problem that maximizes the worst-case coverage fraction across all crop growth stages. Since each objective evaluation requires expensive ray-tracing simulations across all stages, we adopt a Gaussian-process Bayesian optimization~(GPBO) framework that builds a probabilistic surrogate of the robust objective using ray tracing. On a $1\,\text{km}^2$ multi-crop farm with three distinct crop zones at $3.5\,\text{GHz}$, the proposed scheme achieves $72.8\%$ worst-case coverage with $K{=}3$ BSs in fewer than fifty ray-tracing evaluations, outperforming budget-matched state-of-the-art approaches by at least $4.6\,\text{pp}$ across all four seasonal stages.

0

cs.NI 2026-07-02

LLMs turn natural language into valid network topologies

by Kholoud El-Habbouli, Fen Zhou +1 more

An LLM-Based Framework for Intent-Driven Network Topology Design

A pipeline with validation steps lets models meet structural and connectivity requirements across scenarios, enabling better model choice fo

abstract click to expand

Designing deployable and resilient network topologies from natural language requirements remains a challenging problem in network automation. This work investigates the ability of Large Language Models (LLMs) to generate structurally valid and constraint-compliant network topologies through a constraint-driven pipeline combining hierarchical modeling and systematic validation. The framework is evaluated via a multimodel comparison of proprietary and open-weight LLMs across four realistic network scenarios released as a public dataset. We assess structural correctness using node and edge F1-scores against reference topologies, and evaluate resilience through server and content connectivity metrics. In addition, we analyze common failure modes, including interface mismatches and directional inconsistencies in generated topologies. Overall, this work provides a systematic benchmark for understanding how LLMs handle structural and resilience constraints in topology synthesis, and supports informed model selection for AI-driven network design.

0

cs.NI 2026-07-01

MeshDNS resolves DNS in 0.47 ms on ESP8266 IoT chips

by Asif Mahbub, Md. Abir Hossain +1 more

MeshDNS: A Cooperative DNS Resolution Framework for Resource-Constrained IoT Networks

Hash summaries and signed quorums let constrained nodes outperform mDNS while blocking faulty peers under shared-key admission.

abstract click to expand

Domain Name System (DNS) resolution in Internet of Things (IoT) networks presents unique challenges due to resource constraints, unreliable connectivity, and security vulnerabilities. Traditional centralized DNS architectures introduce single points of failure. This paper presents MeshDNS, a cooperative DNS resolution framework designed for resource-constrained IoT environments operating under shared-key admission. MeshDNS employs a decentralized architecture where nodes maintain cache awareness using hash-based summaries and secure cold-cache misses via Ed25519-signed, identical-answer quorum voting. Our implementation on commodity ESP8266 microcontrollers (sub-50 KB usable RAM, 80 MHz) achieves a 0.47 ms warm-cache resolution, outperforming native mDNS baselines (1.39 ms). To secure initial cold-cache misses, MeshDNS trades a predictable ~1.3-1.7s cryptographic penalty to successfully isolate Byzantine faults among admitted peers. Assuming a threat model where physical hardware extraction remains out of scope, MeshDNS demonstrates Byzantine fault isolation. We validated the framework via a 5-node physical testbed and discrete-event simulations scaling to 1,000 nodes; the results demonstrate that MeshDNS maintains resilient local name caches for persistent edge telemetry under network churn. Code is available at https://github.com/mahbubasif/MeshDNS-Artifact.

0

cs.IT 2026-07-01

Dual-regime chain yields optimal AoII push thresholds

by Ismail Cosandal, Sennur Ulukus +1 more

Dual-Regime Absorbing Markov Chain Theory in Remote Estimation: Age-Minimizing Push Policies

A new absorbing Markov construction gives exact SMDP parameters for multi-threshold policies that minimize weighted AoII cost plus energy un

abstract click to expand

For a remote estimation system, we study the optimization of age of incorrect information (AoII), which is a recently proposed semantic-aware information freshness metric. In particular, we assume an information source that observes a discrete-time finite-state Markov chain (DTMC), and occasionally transmits status update packets to a remote monitor which is tasked with remote estimation of the source. For the forward channel from the source to the monitor, we assume the channel delay to be modeled by a general discrete-time phase-type (DPH) distribution, whereas the reverse channel from the monitor to the source is assumed to be perfect, ensuring that the source has perfect information on the AoII and the remote estimate at the monitor, at all times. Push-based transmissions are initiated when AoII exceeds a threshold depending on the current estimation value, i.e., multi-threshold policy. In this very general setting, our goal is to minimize a weighted sum of the time average of a polynomial function of AoII, depending on the remote estimate, and energy consumption from transmissions. We formulate the problem as a semi-Markov decision process (SMDP) with the same state-space of the original DTMC to obtain the optimal multi-threshold policy, whereas the parameters of the SMDP are obtained by using a novel stochastic tool called dual-regime absorbing Markov chain (DR-AMC), and its corresponding absorption time distribution named as dual-regime DPH (DR-DPH). The proposed method is validated with numerical examples using comparisons against other policies obtained by exhaustive search, and also various benchmark policies.

0

cs.NI 2026-07-01

Relay extracts semantic meaning from latent codes without source data

by Yalin E. Sagduyu, Tugba Erpek +2 more

Semantic Leakage and Privacy Preservation in Relay-Assisted Semantic Communications

This exposes a privacy flaw in semantic comms; adversarial training widens the accuracy gap at the relay while preserving receiver performan

abstract click to expand

Semantic communication (SemCom) has emerged as a promising paradigm in which the transmission of task-relevant information is prioritized over raw data, enabling efficient and robust communication under resource and channel constraints. In this paper, the privacy implications of relay-assisted SemCom systems are studied, where the intermediate relay node operates directly on learned latent representations. It is shown that the relay, even without access to source data, can reliably infer semantic meaning and reconstruct signals with performance comparable to that of the legitimate receiver, revealing a fundamental privacy vulnerability of semantic representations. To address this issue, an iterative adversarial training framework is proposed in which a strong, adaptively trained eavesdropper at the relay is explicitly accounted for. The proposed approach alternates between optimizing the relay's eavesdropping function and the legitimate system, resulting in representations that preserve semantic decoding performance at the intended receiver while degrading semantic inference at the relay. The semantic accuracy gap between the legitimate receiver and the eavesdropper is significantly enlarged across channel conditions. Importantly, this protection is achieved in a stealthy manner, with high reconstruction fidelity maintained while semantic leakage is selectively suppressed.

0

cs.NI 2026-07-01

Heterogeneous GNN gives real-time LEO satellite associations

by Aruna Jayarajan, N. Cameron Matson +1 more

LEO Satellite Network Orchestration with Heterogeneous Graph Neural Networks

Distinct node types for satellites, gateways and cells let unsupervised training balance full coverage against load without repeated optimiz

abstract click to expand

Low Earth Orbit (LEO) satellite constellations are becoming essential for expanding global Internet access, especially in remote and under-served areas. However, their highly dynamic nature, arising from network mobility, introduces complex coordination challenges between the dynamic satellites and the ground nodes (gateways and terrestrial devices). This is underscored by limited satellite visibility windows and spatially imbalanced user traffic demands. Local association (cell-satellite-gateway) strategies, such as nearest-satellite or greedy load-based selection, result in partial terrestrial coverage or lead to load imbalance that affects traffic demand fulfillment. Network-driven orchestration through centralized optimization can strike an efficient balance between these two key objectives, but is often computationally intensive for periodic operation and real-time deployment. This work presents a learning-based network orchestration framework, NEO-GNN, that models a satellite-ground network as a dynamic spatiotemporal graph. In contrast to prior works, it employs a heterogeneous Graph Neural Network (GNN), where satellites, gateways, and ground cells are modeled as distinct node types to capture their varied visibility and networking capabilities. They are trained in an unsupervised manner using tailored loss functions to balance the dual requirements of coverage and utilization, and produce efficient, real-time association decisions during inference. Evaluations show that NEO-GNN delivers complete ground-cell coverage, improves traffic demand satisfaction through balanced satellite and gateway use, and remains robust under dynamic visibility and partial satellite failures. NEO-GNN provides a scalable and efficient alternative to traditional optimization methods for real-time network orchestration in bent-pipe LEO satellite systems.

0

cs.NI 2026-07-01

V2V sharing lets vehicles skip redundant image patches in 6G uplink

by Hamidreza Mazandarani, Masoud Shokrnezhad +2 more

Semantic-Aware Multiple Access via Spatial Redundancy Exploitation for Uplink-Dominant 6G Use Cases

By exchanging selected patches first, the base station reconstructs full scenes from fewer unique transmissions.

abstract click to expand

Emerging uplink-dominant 6G use cases, such as cooperative vehicular streaming, require efficient transmission of high-volume visual data over limited wireless resources. While semantic communications can reduce traffic by prioritizing task-relevant content, most existing approaches treat users independently and therefore overlook spatial redundancy among nearby devices' observations. This paper proposes a semantic-aware multiple access scheme that exploits overlapping fields of view among vehicular users to reduce redundant uplink transmissions. We formulate a joint perception and transmission control problem in which users decide which image patches to transmit, when to transmit them, and over which channel, subject to communication constraints. To address the resulting complexity, we introduce a practical two-phase approach. First, nearby vehicles share selected observation patches over Vehicle-to-Vehicle (V2V) links to calculate inter-user spatial redundancy. Second, users transmit only semantically important, non-redundant patches to the base station, where observations can be reconstructed using the received patches and complementary views from neighboring vehicles. Simulation results in a dense urban vehicular scenario demonstrate that our approach improves the proportion of users who achieve high-fidelity reconstruction, highlighting the potential of semantic-aware multiple access for sustainable and resource-efficient 6G uplink systems.

0

cs.NI 2026-07-01

5G ToD support hinges on TDD bandwidth split

by M.Carmen Lucas-Estañ, Baldomero Coll-Perales +5 more

Support of Teleoperated Driving with 5G Networks

Study shows uplink-downlink allocation and internet delays limit how many vehicles can operate and meet strict latency targets.

abstract click to expand

Teleoperated driving (ToD) can support autonomous driving under complex or unexpected traffic scenarios that an autonomous vehicle may not understand or be able to handle. In ToD, autonomous vehicles transmit video feeds and perception data to the remote control center. The operator uses this data to understand the driving environment and remotely control the vehicle that can take over the control once the scenario is resolved. ToD requires reliable and low latency communications between the vehicle and the ToD control center. This study analyzes the feasibility to support ToD with 5G networks. The study demonstrates that the feasibility strongly depends on the bandwidth and the Time Division Duplexing (TDD) frame structure that conditions how the bandwidth is distributed between uplink and downlink transmissions. The study also shows that scaling the number of 5G-supported ToD vehicles requires the vehicles to reduce the video bitrates. The study also shows that traditional centralized 5G network deployments may be challenged by some of the most stringent ToD latency requirements due to the latency introduced by the Internet connection to the ToD control center.

0

cs.NI 2026-07-01

5G scheduling coordinates with TSN to carry more timed flows

by M.Carmen Lucas-Estañ, Ana Larrañaga +2 more

Configured Grant Scheduling for the Support of TSN Traffic in 5G and Beyond Industrial Networks

Using packet size, periodicity and arrival details, the scheme supports additional flows with differing periods compared with existing metho

abstract click to expand

5G and beyond networks can facilitate the digital transformation of manufacturing and support more flexible and reconfigurable factories with ubiquitous mobile connectivity. This requires integrating 5G networks with industrial networks that increasingly rely on TSN (Time Sensitive Networking) to support deterministic communications with bounded latencies. Deterministic communications are critical for many industrial applications, but 5G does not natively support deterministic communications. To address this limitation, this study proposes the coordination of the 5G and TSN schedulers and presents a novel 5G configured grant scheduling scheme to support TSN traffic. The scheme uses information about the characteristics of the TSN traffic (packet size, periodicity, and arrival time) to coordinate its scheduling decisions with the TSN scheduler. The study demonstrates that the proposed scheme outperforms the state-of-the-art in the capacity to support multiple TSN traffic flows with different periodicities.

0

cs.NI 2026-07-01

Latency descriptors enable 5G slicing for aperiodic factory traffic

by M. Carmen Lucas-Estañ, Jan García-Morales +1 more

Latency-Sensitive 5G RAN Slicing for Deterministic Aperiodic Traffic in Smart Manufacturing

Bandwidth-only slicing cannot guarantee timing for critical unpredictable industrial messages.

abstract click to expand

5G and beyond networks will support the digitalization of smart manufacturing thanks to their capacity to simultaneously serve different types of traffic with distinct QoS requirements. This can be achieved using Network Slicing that creates different logical network partitions (or slices) over a common infrastructure, and each can be tailored to support a particular type of traffic. The configuration of the Radio Access Network (RAN) slices strongly impacts the capacity of 5G and beyond to support critical services with stringent QoS requirements, and in particular deterministic requirements. Existing RAN Slicing solutions only consider the transmission rate (or bandwidth) requirements of the different services to partition the radio resources. This study demonstrates that this approach is not suitable to guarantee the stringent latency requirements of deterministic aperiodic traffic that is characteristic of industrial critical applications. We then propose designing RAN slices using descriptors that consider both the services' transmission rate and latency requirements, and demonstrate that this approach can support critical services that generate deterministic aperiodic traffic.

0

cs.DC 2026-07-01

Pipeline overlap cuts split learning latency on edge networks

by Chenyu Liu, Zhaoyang Zhang +4 more

AC²P²SL: Adaptive Communication-Computation Pipeline Parallel Split Learning over Edge Networks

Micro-batch parallelism overlaps communication and computation, shortening training time while keeping data local on user devices.

abstract click to expand

In wireless edge networks, split learning (SL) enables base station (BS) to utilize the distributed data and computing power across user equipments (UEs) to achieve collaborative model training while protecting local data privacy. However, the inherent sequential execution of computation and communication processes in conventional SL usually leads to long training times. To overcome this limitation, this paper proposes an adaptive communication-computation pipeline parallel split learning (AC$^2$P$^2$SL) framework. By conceptualizing the communication and computation processes of UEs and the BS as a unified pipeline, AC$^2$P$^2$SL achieves fine-grained pipeline parallelism across multiple micro-batches. Through this approach, effective overlapping of communication and computation is achieved which results in significant reduction of the overall training latency. Moreover, by considering the system constraints in the communication, computation, and storage dimensions as well as the heterogeneity of UEs, we formulate a joint optimization problem to minimize the training time and propose a corresponding split and pre-allocation algorithm to further enhance the pipeline efficiency. Additionally, accounting for the practical dynamic environments for the UEs, we design an adaptive re-allocation strategy to enhance the system resilience. Extensive experimental results demonstrate the effectiveness and robustness of AC$^2$P$^2$SL in reducing training time while ensuring data privacy preservation.

0

cs.IT 2026-07-01

Dual-agent learning tunes RIS phases and power for mobile tracking

by George Stamatelis, Hui Chen +2 more

Active Sensing for RIS-Aided Tracking and Power Control: A Hybrid Neuroevolution and Supervised Learning Approach

Hybrid neuroevolution and supervised training lets the system handle discrete phases and one-bit feedback while beating Kalman and particle

abstract click to expand

This paper studies energy efficient tracking of power-limited mobile users with the assistance of a Reconfigurable Intelligent Surface (RIS). Since localization pilot transmissions dominate the energy budget of power-constrained devices, we introduce a low-overhead feedback link from the Base Station (BS) to the user to enable dynamic uplink power control. To navigate the discrete and decentralized nature of this active sensing problem, we propose a novel Dual-Agent (DA) deep learning framework that jointly optimizes the discrete RIS phase profiles and the UE's transmit power in real time. Specifically, our approach employs a hybrid training methodology integrating the neuroevolution paradigm with supervised learning, effectively overcoming the non-differentiability of discrete phase responses from the RIS unit elements and the strict information bottleneck of single-bit feedback messages for pilot power control. The proposed DA active sensing framework can be applied with both single- and multi-antenna BSs, the latter with only minor modifications in the structure of one NN: an additional output branch with appropriate structure is included for the latter case to select a valid digital combiner from a finite set. Extensive numerical simulations demonstrate that the proposed scheme achieves highly accurate and robust tracking across diverse target motion models, outperforming extended Kalman and particle filters, as well as, machine learning-based trackers. Furthermore, in static localization, it is shown to significantly outperform traditional fingerprinting schemes, deep reinforcement learning baselines, and standard backpropagation-based estimators.

0

cs.NI 2026-07-01

Covert methods secure and speed LLM edge networks

by Yuanai Xie, Jiaxin Chen +1 more

Beyond Wireless Security: Covert Communications in Large Language Model-enabled Edge Networks

Proposed framework minimizes latency while meeting strict security needs for AI content services.

abstract click to expand

Large language model (LLM)-enabled edge networks (LLMENs) offer mobile users high-quality and low-latency AI-generated content services in the 6G era. However, unlike typical edge networks, LLMENs present unique security challenges due to the inherent complexity of LLMs, their high computational overhead, and continuous interactions with users. Specifically, both frequent user interactions (i.e., queries and responses) over wireless channels and potential electromagnetic information leakage from intensive LLM computations make LLMENs susceptible to various security threats, such as eavesdropping, jamming, prompt poisoning, and prompt injection attacks. Since existing countermeasures against these attacks often incur prohibitive overhead, developing holistic, efficient, and secure privacy protections for LLMENs is crucial. This article first reviews the vulnerabilities of LLMENs, outlines various attacks, and analyzes the drawbacks of existing countermeasures. To overcome these limitations, we propose a covert communications (CC) and computations approach to enhance both the overall security and efficiency of LLMENs. Furthermore, various supplementary solutions are developed to improve the covertness of this framework. Finally, our approach is further evaluated through a case study where the total latency is minimized under stringent communication and computational security requirements. Numerical results demonstrate the proposed approach's effectiveness in enhancing both privacy protection and the execution efficiency of LLM tasks.

0

cs.NI 2026-06-30

Budget router skips weak model to trace best accuracy curve

by Wei Geng, Nitinder Mohan +1 more

Budget-Adaptive Routing: Skipping the Weak When the Strong Answers Anyway

Two offline thresholds let the system pick the better of skipping or running the weak detector, matching top accuracy at every budget.

abstract click to expand

Edge-cloud inference collaborations are often designed with a routing estimator that decides whether to offload each frame from weak models at the edge to stronger models in the cloud. Existing systems place the routing estimator after the weak detector, so the weak forward pass still runs even on frames that are later offloaded. In this paper, we argue that this weak-conditioned design can be suboptimal when the offload budget varies. First, we present a competitive weak-skipping estimator (0.153 GFLOPs, about 29x lighter than the weak detector at 4.49 GFLOPs) that extracts routing signal from raw pixels, outperforming the common after-weak placement weak-conditioned baselines. Second, we show that neither weak-skipping nor weak-conditioned placement dominates across the full operating curve, and we propose budget-adaptive routing, which selects between them by offload budget via two offline-tuned thresholds. On PASCAL VOC, our budget-adaptive router traces the upper accuracy envelope of both fixed placements across the operating range. Our method reduces per-frame latency by up to 19.1 ms (about 30% lower at rho = 0.9). Besides outperforming SOTA methods, it is surprisingly stronger than the strong model (+1.7 pp over the strong model's peak mAP) at some operating points with far less compute. Artifacts are available at https://github.com/ViGeng/bgt-ada

0

cs.NI 2026-06-30

Mini-cars cross intersections without stopping via central scheduler

by Lorenzo Farina, Vittorio Todisco +12 more

A Practical Implementation of Day-3 Cooperative Intersection with Automated Connected Mini-Cars

1:10-scale vehicles exchange wireless messages with a controller to receive speed profiles that eliminate stops at a physical intersection.

abstract click to expand

Cooperative driving enabled by connected and automated vehicles is expected to improve traffic efficiency and safety, particularly at intersections where traditional control mechanisms such as traffic lights introduce delays and unnecessary stops. Although cooperative intersection management algorithms have been widely studied, experimental demonstrations remain limited. This paper presents a real-time demonstration of cooperative intersection management using connected autonomous mini-cars. The testbed consists of multiple 1:10 scale vehicles equipped with autonomous driving capabilities and wireless communication modules that interact with a centralized controller responsible for scheduling their crossing of the intersection. Vehicles approaching the intersection exchange messages with the controller to set the appropriate mobility profile to traverse the intersection without stopping. The demonstration integrates autonomous driving, wireless communication, and cooperative control in a single experimental platform, providing a practical environment for validating cooperative intersection management concepts for future intelligent transportation systems.

0

cs.NI 2026-06-30

CALO guarantees feasible real-time allocation in double-active RIS networks

by Alaa S. Arabiyat, Mohammad J. Abdel-Rahman

CALO: Constraint-Aware Learning Optimization for Joint Resource Allocation in Double-Active RIS-Assisted Wireless Networks

Grouped fractional maps and a regret-driven loss deliver 100 percent feasibility plus faster inference than block coordinate descent.

abstract click to expand

Double-active reconfigurable intelligent surface (RIS)-assisted wireless systems can improve coverage and achievable rate in blockage-dominated environments. Still, their joint resource allocation is challenging due to the coupling among RIS placement, amplification power allocation, and reflecting-element assignment. The resulting problem is linearly constrained, non-convex, and involves both continuous and discrete variables, making conventional iterative solvers such as block coordinate descent (BCD) computationally expensive for real-time deployment. This paper proposes a \underline{c}onstraint-\underline{a}ware \underline{l}earning \underline{o}ptimization (CALO) framework for data-driven joint resource allocation in double-active RIS-assisted networks. CALO reformulates the decision variables into grouped fractional representations and maps them to physical resources through constraint-preserving transformations, ensuring that distance, power, and element-budget constraints are satisfied by construction. A straight-through estimator is incorporated to enable differentiable learning over discrete reflecting-element assignments, while a regret-driven hinge objective uses the BCD solution as a reference and encourages performance improvement beyond solver imitation. Simulation results show that CALO achieves $100\%$ feasibility across all tested configurations, improves the achievable rate over BCD in both urban and rural scenarios, and reduces online inference time by orders of magnitude. These results demonstrate the effectiveness of structure-aware learning for feasible and real-time optimization in active multi-RIS wireless systems.

0

cs.IT 2026-06-30

Belief in age and state guides which sensor to query

by Ismail Cosandal, Sennur Ulukus +1 more

When and Which Sensor to Observe? Timely Tracking of a Joint Markov Source

Model predictive control on the joint distribution cuts weighted age of incorrect information plus sampling costs over delayed erasure links

abstract click to expand

We investigate the problem of remote estimation (at a monitor) of a discrete-time joint Markov process with individual components which can be observed with dedicated sensors. At a given time slot, the monitor has the option of staying idle or sending a pull request to one of the sensors to obtain a partial state value, while the sensors are assumed to have heterogeneous sampling costs. Our goal is to develop a monitor pull policy, i.e., determining when and towards which sensor to send a pull request, in order to minimize a weighted sum of average age of incorrect information (AoII), or in short age, and sampling costs. As the communication model, we assume an erasure channel with a fixed one-slot delay from each sensor to the monitor. In this setting, the monitor does not perfectly know either the state of the process or the age, at any given time. We first obtain a sufficient statistic, namely belief, representing the joint distribution of the age and the current state of the observed process, by using the history of all pull requests and observations. Then, we formulate the optimization problem as a continuous state-space Markov decision process (MDP), namely belief-MDP, for the solution of which we propose two model predictive control (MPC) methods, namely MPC without terminal costs (MPC-WTC), and reinforcement learning MPC (RL-MPC). The effectiveness of the proposed methods is validated by numerical examples.

0

cs.NI 2026-06-30

Low-power trigger selectively backdoors one semantic transmitter

by Yalin E. Sagduyu, Tugba Erpek +2 more

Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Channel

Adversary contaminates training with waveform to alter inference for one user while sparing the other in multiple access semantic system.

abstract click to expand

Semantic communication (SemCom) aims to preserve semantic meaning and task-oriented information beyond conventional message recovery over wireless channels. The adoption of SemCom in shared-access wireless networks introduces new vulnerabilities for multi-user semantic inference. This paper considers a SemCom system for two transmitters communicating with a common receiver over a multiple access channel. Each transmitter maps source information into latent semantic representations, while the receiver jointly reconstructs and classifies the semantic information for both transmitters. A selective over-the-air backdoor (Trojan) attack is presented in which an adversary transmits a low-power trigger waveform over the air and injects it into the shared received signal during training. By transmitting the trigger again during testing, this stealthy, low-power attack selectively manipulates the semantic inference for one transmitter while minimally affecting the inference of the other transmitter. To mitigate this vulnerability, a trigger-aware defense mechanism is developed to preserve correct semantic labels under trigger-contaminated wireless observations. The results demonstrate both the vulnerability of shared-access SemCom systems to selective over-the-air backdoor attacks and the effectiveness of trigger-aware robust training for semantic protection.

0

cs.NI 2026-06-30

Joint compute and routing migration halves mobile AI latency

by Abdirazak Ali Asir Rage, Riccardo Pozza +1 more

SubEdge: A Subscriber-Centric Edge Computing Subsystem in 6G Networks for AI

SubEdge binds each subscriber to a dedicated edge inference instance and moves it with connectivity to maintain 99.92 percent frame delivery

abstract click to expand

Beyond traditional connectivity, 6G is envisioned to transform mobile networks into a distributed fabric that provides native integrated communication, computing, and intelligence services. AI-native terminals (e.g., robots, autonomous vehicles, and smart glasses) require real-time inference from individualised, manufacturer-specific models that cannot be executed on-board nor shared across subscribers, making per-subscriber edge compute the necessary complement to per-subscriber connectivity. Existing Network for AI (Net4AI) architectures provision compute for application providers through shared deployments and do not address per-subscriber provisioning. This paper proposes SubEdge, a Net4AI subsystem that provisions integrated communication and compute resources on a per-subscriber basis, ensuring the coupled migration of both dimensions to maintain service continuity during mobility. SubEdge contributes the computing context--a per-subscriber data structure binding a Subscription Permanent Identifier (SUPI) to its inference container, edge node, and service entitlement--and a mobility-event-driven mechanism that simultaneously migrates the subscriber's compute instance and its traffic-routing policy when the serving cell changes. SubEdge operates as an Application Function over existing Network Exposure Function (NEF) APIs with zero 3GPP core modifications. Experimental evaluation on a real-world testbed shows that SubEdge's mobility-driven joint communication-and-compute migration reduces 95th-percentile latency from 22.9 ms to 12.2 ms with zero packet loss across six mobility events, sustains 99.92% frame delivery for an end-to-end 30 fps inference workload, and completes 1,560 migration operations across batches of up to 50 simultaneously migrating subscribers with 100% success.

0

cs.NI 2026-06-30

Multi-agent LLMs generate network mitigations via attack replay

by Chen Frydman, Aviram Zilberman +7 more

COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies

46.7 percent of outputs stop the attack while keeping connectivity intact, 4.4 times the single-agent rate across tested topologies and scen

abstract click to expand

Mitigating an observed adversary in an enterprise network typically takes weeks of expert work: an analyst derives a mitigation tailored to that adversary, validates it without breaking production, and verifies it disrupts the specific attack. The procedure relies on expert judgment and cannot safely be exercised against the production network. COHORT is the first end-to-end framework to automate this procedure for deployable mitigations. A role-decomposed multi-agent LLM workflow proposes candidates, implements them as real device commands, and refines them through a critique loop, all on a high-fidelity GNS3 emulator running real vendor firmware (firewall, switch, router). Each candidate is evaluated by offensive replay: re-executing the original adversary on the mitigated network for a paired comparison against the unmitigated baseline, rather than the reward-signal or expert-judgment proxies used in prior simulation, hybrid, and configuration-generation work. Two further checks complement replay: a connectivity-regression check (LAN ping and internet HTTP probe) rejects mitigations that disrupt legitimate LAN or internet connectivity, and a cumulative evaluation stacks approved mitigations onto a persistent state to surface compound effects. Across three topologies and four attack scenarios (ransomware, lateral movement, DNS exfiltration, data theft), 46.7% of generated mitigations both disrupt the attack and preserve connectivity under replay, 4.4 times the rate of a single-agent baseline using the same model and tool access. A demo video walking through the framework is available with our released artifacts.

0

cs.NI 2026-06-30

LLMs require new optical enablers for distributed training

by Mëmëdhe Ibrahimi, Qiaolun Zhang +4 more

LLMs and Optical Networks: A Symbiotic Relationship

Geo-distributed LLM training needs WAN-aware algorithms and hollow core fibers while supplying tools for automatic network control.

abstract click to expand

This paper explores the emerging symbiosis between LLMs and optical networks. Massive LLMs require geo-distributed training, which demands advanced optical transport capabilities that require new key technical enablers, as WAN-aware CCL algorithms, ZR+ pluggables, and Hollow Core Fibers. Conversely, LLMs also enable new forms of autonomous network management.

0

cs.NI 2026-06-30

Half the links upgraded to bidirectional hollow-core fiber yields 40% more throughput

by Mëmëdhe Ibrahimi, Giovanni S. Sticca +2 more

Selective Deployment of Bidirectional Hollow-Core Fibers in Hybrid SMF/HCF Optical Networks

Partial bidirectional HCF deployment captures 85% of full-upgrade power savings in hybrid networks.

abstract click to expand

We investigate selectively deploying bidirectional transmission in hybrid Hollow-Core Fiber (HCF) networks. Upgrading 50% of links to bidirectional HCF yields at least a 40% throughput increase compared to unidirectional SMF and captures 85% of the power consumption reduction of a full unidirectional HCF network upgrade.

0

cs.NI 2026-06-30

Uncertainty ellipses cut V2X prediction load tenfold

by Felipe E. Valle, Oscar Amador +3 more

Scalable Intention Sharing for ETSI VAMs

Constant-size ellipse messages from EKF forecasts sustain multi-second horizons on real cyclist GNSS tracks.

abstract click to expand

Efficient maneuver coordination in dense V2X environments requires accurate short-term prediction while maintaining low communication and computational overhead. Current European Telecommunications Standards Institute (ETSI)-compliant approaches rely on intention detection and trajectory vector transmission, which scale poorly with neighborhood size and prediction horizon. This paper revisits maneuver coordination from an intention sharing perspective and investigates geometric encodings that enable scalable communication. First, we analyze three ETSI-compliant encodings, trajectory vectors, N-polygons, and uncertainty ellipses, through complexity analysis and simulation-based CPU measurements. Results show that uncertainty ellipses reduce computational complexity by an order of magnitude compared with trajectory vectors while maintaining a constant message size. Building on this, an Extended Kalman Filter is used to generate short-horizon predictions, which are encoded as uncertainty ellipses to represent the intended maneuver. The prediction pipeline is evaluated using real-world GNSS trajectories collected from cyclist maneuvers on a controlled test track, demonstrating that the approach achieves reliable multisecond prediction horizons while maintaining scalability for dense V2X environments.

0

cs.IT 2026-06-30

Diffusion model beats LSTM on LEO satellite traffic forecasts

by Shaoyou Ao, Yong Niu +3 more

LEOSTP: A Spatio-Temporal Traffic Prediction Framework for LEO Satellite Networks

LEOSTP adds geographic population and POI data to a diffusion-Transformer pipeline and records lower error than ARIMA, SVR, LSTM and Transfo

abstract click to expand

With the evolution of next-generation mobile communication networks and the commercial boom of Low Earth Orbit (LEO) satellites, globally covered satellite networks are gradually becoming a crucial infrastructure for massive user access and seamless connectivity. Accurate traffic prediction is crucial for maintaining the quality of service (QoS) and resource allocation efficiency in satellite networks. However, existing methods struggle to effectively address the three major challenges of LEO networks: highly complex temporal dynamics caused by satellite cross-regional movement, multivariate dependencies in multi-satellite collaboration, and strong spatial heterogeneity driven by user distribution, human activity intensity, and local geographic environments. In this article, we propose a LEO Satellite Traffic Predictor (LEOSTP) framework, a diffusion model-based end-to-end model that forecasts future satellite traffic by jointly leveraging historical traffic patterns and contextual characteristics of the corresponding service regions. The framework consists of two core modules: 1) The general traffic feature extractor module combines the diffusion process with a Transformer architecture to model the multi-scale temporal features of the traffic itself. 2) The external condition encoder module integrates geographic semantic information such as population distribution, point-of-interest (POI) distribution, and local time into the prediction process through a Transformer-based encoder. In this way, the model captures the deep correlation between the external environment and traffic dynamics. Experimental results based on large-scale simulated constellation data show that LEOSTP significantly outperforms traditional statistical models such as ARIMA and SVR, and classical sequence models including LSTM and Transformer, in prediction accuracy.

0

cs.IT 2026-06-29

DCC limits cause over 4x daily swings in vehicle update age

by Yousef AlSaqabi

Age of Information Under DCC Rate Constraints for V2I Broadcast Along Urban Corridors

Hyperbolic density dependence dominates AoI along urban corridors; cooperative upstream estimates cut it by up to 66 percent

abstract click to expand

ETSI Decentralized Congestion Control (DCC) limits roadside unit (RSU) broadcast rates based on channel load, yet its impact on age of information (AoI) for vehicle-to-infrastructure updates remains uncharacterized under real traffic. We derive the AoI of DCC-constrained V2I broadcast, revealing a hyperbolic density dependence that induces diurnal AoI variation exceeding 4 times on a four-RSU corridor, with the DCC target CBR parameter as the dominant control. We propose a cooperative policy exploiting upstream spatial traffic correlation to improve channel load estimation, with a safeguard ensuring non-negative gains. Evaluated on a 5-day, 762,050-vehicle trace from Kuwait City, the policy reduces corridor AoI by 5% at moderate and up to 66% at conservative DCC settings.

0

cs.NI 2026-06-29

Cooperative scheduling cuts RSU energy use 59.5% in corridors

by Yousef AlSaqabi

Cooperative RSU Sleep Scheduling for Green V2I Corridors

Predictive wake-up from shared signals adds 7.7 points savings over independent methods at high traffic correlation.

abstract click to expand

As vehicle-to-infrastructure (V2I) deployments scale, roadside units (RSUs) that consume 10-25W continuously yet serve negligible traffic during off-peak hours represent a growing source of energy waste. Sleep scheduling can exploit the pronounced diurnal variation in urban traffic, but the WAVE service restoration overhead of up to 100ms nearly exhausts the 3GPPTS~22.185 latency budget, making independent sleep decisions risky. This paper proposes a cooperative framework in which upstream RSUs share traffic detection signals with downstream neighbors via infrastructure-to-infrastructure links, enabling predictive wake-up that exploits spatial correlation between adjacent intersections. The framework is formulated as a constrained Markov decision process and decomposed into per-RSU subproblems solvable by value iteration. Four algorithms of increasing sophistication are evaluated on real hourly traffic data from four consecutive signalized intersections in Kuwait City, comprising a total of 762,050 vehicles over five days. The cooperative algorithm reduces corridor energy consumption by 59.5% relative to always-on operation while maintaining 99% latency compliance, and provides 7.7 percentage points of additional savings over independent per-RSU optimization at downstream RSUs with spatial correlation \r{ho} >= 0.97. Extrapolated to a 200-RSU urban deployment, the cooperative approach yields an estimated 5.25 tonnes of CO2 reduction per year.

0

cs.NI 2026-06-29

A stateless network-aware ABR policy for IPFS video streaming recomputes bitrates from…

by Iliya Mirzaei, Shabnam Jafarzade Mojaveri +1 more

Stateless Network-Aware Adaptive Bitrate Streaming over IPFS

Local signals plus client-carried state replace synchronized provider state and raise QoE up to 6x in faulty conditions.

abstract click to expand

Modern content delivery is increasingly decentralized, improving availability, cost, and reach for geographically distributed users. The InterPlanetary File System (IPFS) is a promising approach that uses content-based identifiers distributed across a global peer-to-peer network. Although IPFS improves fault tolerance, resilience, and censorship resistance, its unpredictable environment introduces significant performance variability that limits conventional Adaptive Bitrate (ABR) streaming and degrades Quality of Experience (QoE). Recent network-aware ABR solutions address this by incorporating IPFS-specific information into bitrate decisions. However, they rely on maintaining continuously synchronized state across consumers and providers, which can quickly become stale under peer churn, provider migrations, network partitions, and changing content distributions, making existing policies less effective. We investigate whether network-aware ABR can remain effective without synchronized adaptation state, and present a stateless network-aware ABR policy for IPFS-based video streaming. Our approach replaces provider-stateful adaptation with an observation-driven policy that recomputes the bitrate for each segment using only locally observable request-time signals. To preserve adaptation context without provider-side state, the client embeds its adaptation state in HTTP headers, keeping it under client control and carried transparently across requests. By eliminating cross-provider state synchronization, the framework improves robustness to failures and network reconfigurations while simplifying deployment at scale. Early results show the approach maintains high QoE in faulty conditions, improving it by up to roughly 6x over existing solutions. These findings demonstrate that stateless network-aware adaptation provides a practical and scalable foundation for decentralized video delivery.

0

cs.LG 2026-06-29

Starlink latency signatures tied to infrastructure and dish distance

by Xiang Shi, Yifei Zhang +1 more

Deciphering Region-Level Signatures from Latency Measurements in LEO Satellite Internet

Minimum RTT distinguishes five regions at 83 percent short-term accuracy; performance falls over longer windows

abstract click to expand

Low-Earth orbit (LEO) satellite Internet has become an indispensable infrastructure that provide growing coverage for global users. Despite extensive measurement efforts, the principles underlying region-level performance characteristics remain insufficiently understood, limiting the ability to identify region-specific latency signatures under dynamic network conditions. In this paper, we formulate the problem of region-level latency characterization using Starlink round-trip time (RTT) measurements from the public LENS dataset. We then propose a hierarchical analytical framework that transforms raw RTT sequences into multi-scale statistical features for cross-region comparison. Using data from five geographically representative regions, we demonstrate that latency differences are strongly associated with deployment factors, particularly infrastructure availability and Starlink dish-to-Point-of-Presence distance. Mutual information analysis identifies minimum RTT as the most discriminative feature, which is further supported by XGBoost-based feature importance. The proposed model well achieves 83% accuracy on short-term data. However, its performance degrades over longer periods, indicating limited temporal generalization and motivating the need for adaptive models and feature representations for long-term performance in the future.

0

cs.NI 2026-06-29

LLMs extract spec constraints to test protocol boundaries and find 42 bugs

by Rathin Singha, Kuan Qian +7 more

CornerCase: Automated Extremal Testing of Protocol Implementations using LLMs

CornerCase generates extremal tests for HTTP, DNS, BGP, SMTP and QUIC, leading to 26 acknowledged issues

abstract click to expand

Many software bugs in network protocol implementations arise near specification boundaries, such as inputs just within or outside allowed ranges, or messages that are valid in isolation but invalid in a given state. From the SSL Heartbleed exploit to TCP Christmas Tree packets, boundary inputs have repeatedly exposed critical weaknesses, yet remain under-tested by existing techniques such as fuzzing and model-based testing. We present CornerCase, an automated extremal testing approach that systematically targets such boundary behaviors. Our key idea is to decompose test generation into two stages: first, large language models (LLMs) extract explicit validity constraints from protocol specifications (e.g., RFCs) in a structured, section-by-section manner; second, extremal test cases are generated at or near the boundary of each constraint. These tests are executed across multiple implementations, and differential testing identifies inconsistencies. We evaluate CornerCase on widely used implementations of HTTP, DNS, BGP, SMTP, and QUIC, uncovering many previously unknown bugs. For example, the HTTP server h2o enters a redirect loop when processing URLs containing encoded null bytes. Overall, we used CornerCase to identify and file 42 anomalies; to date 26 have been acknowledged as bugs and 18 fixed, with others under active investigation

0

cs.NI 2026-06-29

Software overlay brings TSN timing to ordinary networks

by Mohammadparsa Karimi, Majid Nabi +4 more

V-TSN: A Software-Defined TSN Overlay for General-Purpose Networks

Cloud tests report sub-200 microsecond clock offset plus virtual TAS and CBS shapers without hardware

abstract click to expand

Time-Sensitive Networking (TSN) extends Ethernet with deterministic communication for time-critical applications such as industrial automation, in-vehicle networks, and cyber-physical systems. However, realizing TSN behavior without dedicated hardware is difficult. During design and validation, offline simulation cannot run application software at real-time speed when costly specialized TSN hardware is not (yet) available. At deployment time, many systems run on general-purpose and cloud networks with no native TSN support, where provisioning full TSN hardware is unnecessary or impractical for applications that tolerate relaxed timing. In this paper, we introduce Virtual Time-Sensitive Networking (V-TSN), a software-defined overlay that realizes gPTP-based synchronization and TSN traffic shaping over general-purpose, non-deterministic networks without specialized hardware. V-TSN runs in real time alongside the unmodified application stack, serving both as a development-time emulation tool and as a cost-efficient deployment option where relaxed timing is acceptable. In a cloud-based deployment, V-TSN achieves an average clock offset below 200 microseconds, it isolates time-critical traffic through a virtual Time-Aware Shaper (TAS), and it enforces per-class bandwidth reservations through a virtual Credit-Based Shaper (CBS).

0

cs.NI 2026-06-29

Attention model aligns slot clocks to cut UWB TDOA variation 9 percent

by Tianyi Lyu, Kefei Tian +3 more

AB-Sync: Attention-Based Slot-Level Clock Synchronization Method for UWB-TDOA Localization Networks

Per-slot clock-speed estimation from neighbor fluctuations raises static accuracy 18.6 percent with no extra messages.

abstract click to expand

Ultra-wideband (UWB) time-difference-of-arrival (TDOA) localization networks provide high-update-rate indoor location services for IoT and cyber-physical applications, but their accuracy depends on nanosecond-level clock synchronization among anchors. Existing wireless clock synchronization (WCS) methods typically estimate clock states at the synchronization-stage or interval level, whereas TDMA-based UWB-TDOA systems localize tags from blinks transmitted in discrete short slots inside each synchronization stage. We identify this granularity mismatch as a source of residual TDOA error and present AB-Sync, an attention-based slot-level clock synchronization method. AB-Sync models the relationship between the slot-specific clock-speed ratio required by a target tag blink and neighboring clock-fluctuation observations, thereby enabling tag-slot-level timestamp mapping without adding extra UWB synchronization messages. On a real UWB-TDOA testbed, AB-Sync reduces the multi-anchor average TDOA ranging STD.V by 9.4% and improves representative static localization accuracy by 18.6% compared with Deferred+3S-KF, the leading low-overhead baseline in our evaluation. In a five-slot multi-tag experiment, AB-Sync consistently improves localization stability across all TDMA slots, reducing STD.V by 5.3% on average and up to 16.2% per slot with no extra UWB synchronization overhead.

0

cs.CR 2026-06-29

Game theory model tracks malware spread under attacker-defender regimes

by Shadeeb Hossain, Kristopher Wilson

GTI-mSEMP Framework : A Proposed Framework to Simulate Malware Propagation with Inclusion of Attacker-Defender Strategy

Simulations in three regimes show how efficiency advantages shift susceptible and recovered node populations in wireless networks.

abstract click to expand

The rapid proliferation of automated, multi-vector malware threats poses a significant risk to heterogeneous, resource constrained cyber-physical networks. Conventional epidemiological models often treat security defenses as static parameters, failing to capture the strategic, asymmetric maneuvers between an attacker and a defender. To address the gap, this paper proposes a Game-Theory-Integrated Modified Multi- Wireless Sensor Epidemic Malware Propagation (GTI-mSEMP) framework. This paper analyzed and compared the operational trajectories of Susceptible (S) and Recovered (R) node populations across three different operational regimes: Balanced Matchup, Exploit Surge and Hardened Defense. Numerical simulation results capture the real-time transient dynamics of the network state variables, demonstrating how the epidemic curve shifts when either the defensive or offensive scaling vectors hold an efficiency advantage. The proposed mathematical and numerical framework provides a rigorous foundation that can be deployed in highly adversarial network environments to evaluate dynamic malware propagation and predict localized node population states.

0

cs.NI 2026-06-29

Host SRv6 flowlet steering cuts tail latency 33% vs ECMP

by Ryo Nakamura, Hiroki Kano +1 more

Host-Driven Flowlet Balancing with Segment Routing over IPv6

By estimating bytes in flight at the host, flowlets are distributed more evenly without any switch state.

abstract click to expand

This paper proposes a fully host-driven method for flowlet balancing with Segment Routing over IPv6 (SRv6). In modern data center networks, load balancing plays a pivotal role in efficiently utilizing multiple paths. Flowlet balancing offers finer granularity in traffic splitting than ECMP and is therefore expected to achieve higher performance. However, deploying flowlet balancing in practice is still challenging due to the scalability issue of switches having to maintain per-flow state. In our approach, hosts detect flowlets in their outgoing traffic and steer them onto specific paths using SRv6. The switches behave as SRv6 nodes in a stateless manner. Each host distributes its flowlets as evenly as possible across paths. As a metric for this load balancing, we introduce a simple model that estimates in-flight bytes on each path. We implemented the proposed method on Linux and evaluated it on a testbed with an SRv6-capable router. The results show that, under fixed-size flows, the proposed method reduces tail latency by 15% and 33% compared with random flowlet balancing and ECMP, respectively. Furthermore, combining the method with dynamically adjusted flowlet timeouts also improves performance under two application workloads.

0

eess.SY 2026-06-29

5G cuts smart grid state estimation delay by factor of 6.5

by Biswajit Kumar Dash, Luis Herrera +1 more

Real-Time State Estimation in Smart Grids over 5G Networks: Experimental Validation Using Raspberry Pis and Typhoon HIL

Hardware tests show accurate estimation and 0.80 s fault detection over commercial 5G, outperforming earlier LTE results.

abstract click to expand

Reliable, low-latency communication is critical for real-time monitoring and control in modern Smart Grids (SGs). The emergence of 5G networks, with enhanced reliability, significantly lower latency, and native support for massive machine-type communication, offers strong potential to enable advanced grid applications such as state estimation (SE) and fault detection. While existing studies investigate 5G for SG use cases, most rely on simulations or analytical models; experimental validation using real hardware and SG data remains limited. This paper fills this gap by presenting a fully experimental validation of real-time SE over a commercial 5G network using a 5G-based multi-node testbed built with Raspberry Pi (RPi)-based SG nodes and a Typhoon Hardware-in-the-Loop (HIL) real-time simulator. We first characterize 5G communication performance using simulated SG data under varying reporting rates and deployment environments by evaluating Key Performance Indicators (KPIs) such as end-to-end delay, jitter, and frame loss. Experimental results show that the worst-case mean delay observed for the 5G is approximately 6.5x lower than that of our previous LTE cat-M study at the corresponding reporting rate. We then stream real-time voltage, current, and phase-angle measurements-generated by an IEEE 4-node feeder model in Typhoon HIL simulator-to a remote Phasor Data Concentrator (PDC) for SE and fault detection. Results demonstrate that 5G-enabled measurements support accurate SE under both steady-state and dynamic load variations. Furthermore, fault-detection experiments confirm reliable and prompt fault detection, with detection delays as low as 0.80 s.

0

cs.NI 2026-06-26

6G air interface needs AI coordination protocols

by Xingqin Lin

Toward AI-Native 6G Air Interface: A 3GPP Perspective on Protocol Framework

Standardization should let vendors choose their own AI while defining how those systems configure, validate, and fall back together.

abstract click to expand

Artificial intelligence (AI) is expected to play an important role in the sixth-generation (6G) air interface design, but making the air interface truly AI-native requires more than applying learning algorithms to individual radio functions. The deeper challenge is architectural: once AI influences how the user equipment and network interpret, predict, and adapt radio behavior, the air interface must provide common protocol semantics for coordinating such intelligence across vendors and deployments. This article presents a 3rd generation partnership project (3GPP) oriented perspective on the protocol framework for AI-native 6G air interface. We argue that standardization should preserve implementation freedom by avoiding prescription of model architectures, training methods, or model weights. Instead, 6G should define the protocol framework needed for interoperable AI operation, including how AI-enabled functions are configured, validated, activated, monitored, and safely reverted to conventional operation. Neural receiver assisted reference signal adaptation is used as a case study to concretely show this broader architectural shift.

0

cs.NI 2026-06-26

LEO satellite networks support 600 MB bursts at 100 Gbps

by Thomas Roethig, Sleman Mouammar +3 more

Maximum Achievable Burst Size in All-Optical Satellite Networks

WDM optical burst switching yields 100 MB larger bursts in low-altitude than high-altitude constellations.

abstract click to expand

We analyze the maximum burst size achievable in all-optical satellite networks across different constellations. With a 100 Gbps uplink capacity, a WDM-based optical burst switching network supports burst sizes of up to 500 MB in high-altitude LEO constellations and 600 MB in low-altitude LEO constellations.

0

cs.NI 2026-06-26

Solver design lifts 14B model to 0.88 correctness on network tasks

by Gianmaria Frigo, Davide Saladino +5 more

Toward Agentic SysAdmin: Rethinking System Administration with AI Agents

24000-run study shows locally deployable models match trillion-parameter systems under the right solver configuration

abstract click to expand

The growing complexity of computer networks, driven by cloud-native architectures, heterogeneous devices, and distributed systems, places increasing pressure on network administrators who must simultaneously manage configuration, troubleshooting, and security under tight operational constraints. Large Language Models (LLMs) have emerged as a promising tool to assist and partially automate these tasks, yet their systematic evaluation in networking scenarios remains an open challenge. Existing benchmarks rely on static reference outputs or manual expert validation, neither of which scales to the diversity of real-world network states or to the variety of orchestration strategies -- from monolithic prompting to fully agentic pipelines --through which LLMs are increasingly deployed. In this paper, we present NetLLMeval, a framework for automatically evaluating LLM-based systems on network administration tasks by leveraging live network emulation to derive ground truth without human intervention. Through a full-factorial study of 24000 runs spanning 10 foundation models, 4 solver architectures, 10 task types, and 6 network topologies of increasing complexity, we show that solver design has a great impact on accuracy -- lifting a 14B open-weight model from 0.43 to 0.88 correctness -- and that such locally-deployable models can match trillion-parameter frontier systems under the right configuration. NetLLMeval is released open-source to support reproducible benchmarking of future models and solver designs.

0

cs.NI 2026-06-26

RIS changes secondary links even at different frequencies

by Cyrille Morin (MARACAS), Leonardo S Cardoso (CITI +6 more

An Experimental Assessment of the Spatial and Frequency Selectivity of Reconfigurable Intelligent Surfaces

Testbed measurements show power and phase shifts persist outside the surface's nominal range and are not removed by carrier separation.

abstract click to expand

This work investigates the impact of reconfigurable intelligent surfaces (RIS) on radio links other than the one for which the RIS configuration is optimized. We consider three different scenarios in which a secondary communication link could be affected by a RIS whose configuration is optimized for a primary communication link operating in the vicinity, on the same or on different frequencies. This question is investigated experimentally in the FR1 band, using the CorteXlab radio testbed and a Greenerwave RIS. We show that the impact, in terms of received power and impact on the channel phase of the secondary link, is significant even outside of the nominal frequency range of the RIS, and is not mitigated by carrier frequency separation between the two communication links.

0

cs.NI 2026-06-26

Resource stability outperforms load optimization for CPMs in 5G NR-V2X

by Vittorio Todisco, Mattia Andreani +2 more

5G NR-V2X Scheduling Approaches for CPM Variable Size Traffic

SPS with padding converges to stable allocations while dynamic scheduling and aggressive reselection increase collisions under realistic var

abstract click to expand

Collective perception messages (CPMs) introduce significant packet size variability due to dynamic object inclusion and periodic security overhead. While 5G NR-V2X Mode 2 typically employs semi-persistent scheduling (SPS) designed for periodic traffic with relatively stable packet sizes, the impact of realistic CPM-driven size fluctuations on distributed resource allocation remains insufficiently understood. This paper presents a comparative system-level evaluation of NR-V2X Mode 2 scheduling strategies under variable-size CPM traffic reconstructed from real-world perception datasets. We analyze dynamic scheduling and multiple SPS-based approaches, including padding-based allocation, aggressive size-driven reselection, and modulation and coding scheme (MCS) adaptation. Results show that packet size variability can significantly degrade reliability when scheduling stability is compromised. In particular, dynamic scheduling and aggressive reselection increase collision probability due to frequent resource reallocations. In contrast, SPS with padding converges to a stable resource allocation and provides robust performance, while MCS adaptation achieves the highest average packet reception ratio but with uneven reliability across packet types. The findings demonstrate that, under realistic CPM traffic, stability of resource usage is more critical than instantaneous load optimization, and provide design guidelines for CPS deployment over NR-V2X Mode 2.

0

eess.IV 2026-06-25

Standard ABR boosts throughput for time-shifted MoQ clients

by Abanisenioluwa Orojo, Tanvir Redoy +2 more

An Evaluation of ABR Switching for Time-Shifted Clients in MoQ

Unmodified algorithms work for shifted playback and raise performance after rebuffering in simulations.

abstract click to expand

Media over QUIC enables ultra low latency video streaming over QUIC, but its default quality-switching semantics risk introducing playback gaps during periods of network congestion. The in-progress SWITCH specification for MOQ Transport aims to streamline rate adaptation for MoQ. In this work, we characterize the performance of SWITCH-style Adaptive Bitrate (ABR) for both live and time-shifted clients in a Mininet simulated topology. We validate that standard ABR algorithms can be directly applied to time-shifted playback without modification, yielding substantially higher throughput. We demonstrate that a subscriber can experience increased overall throughput after a rebuffering scenario, and we identify focal points for further optimizations of MoQ ABR switching.

0

cs.NI 2026-06-25

Auction-learning method lifts SAGIN task success by 8.7 points

by Xuli Cai, Poonam Lohan +2 more

HALO: Hierarchical Auction-assisted Learning for Offloading in SAGIN

HALO's auction association plus hierarchical PPO maintains higher success rates than PPO, DDPG, and SAC across varying traffic loads.

abstract click to expand

In this paper, we investigate delay-aware task offloading and resource scheduling in a three-tier space-air-ground integrated network (SAGIN) consisting of IoT devices, UAV edge nodes, and a high-altitude platform station (HAPS). We formulate joint task association and continuous resource control (including bandwidth, transmit power, and CPU frequency allocation) as a non-convex mixed-integer nonlinear programming (MINLP) problem, which is inherently NP-hard. To capture fine-grained system dynamics, we introduce a macro-micro slot model that tracks cumulative transmission and computation progress over time. Based on this model, we propose HALO, a hierarchical auction-assisted learning framework that combines auction-based task association with hierarchical Proximal Policy Optimization (HPPO) for resource allocation. Simulation results under different traffic loads show that HALO consistently outperforms representative deep reinforcement learning (DRL) baselines. In particular, HALO achieves an average improvement of 8.7 percentage points in task success rate over PPO (corresponding to an 11.4% relative gain) and shows consistently greater robustness than DDPG and SAC, with relative improvements of 32.4% and 89.9%, respectively. These results highlight HALO's ability to maintain stable and efficient performance under varying traffic conditions, making it well-suited for delay-sensitive SAGIN environments.

0

cs.NI 2026-06-25

Lyapunov controller eliminates 5G bufferbloat in factories

by Kouros Zanbouri, Md Noor-A-Rahim +2 more

Lyapunov Optimization based Queue-aware Traffic Shaping for 5G-TSN in Industrial Environments

Adapts rates to current queues during metal blockages, avoiding latency spikes on reconnection without channel predictions.

abstract click to expand

Manufacturing companies look increasingly at Private 5G networks to manage Automated Guided Vehicles (AGVs). While 5G promises Ultra-Reliable Low Latency Communication (URLLC), its service quality is challenged by industrial environments characterized by dense metallic structures, which frequently cause line-of-sight (LOS) blockage events, causing deep fades in received signal levels that can degrade channel capacity to near-zero. Standard transport protocols and rate adaptation mechanisms fail to react sufficiently fast to these deep fades, resulting in bufferbloat and latency spikes that violate safety margins. In this paper, we propose a cross-layer rate control algorithm based on Lyapunov Drift-plus-Penalty theory. The proposed controller dynamically optimizes the trade-off between service utility and queue stability based on instantaneous buffer states, without requiring predictive channel models. We validate the approach using a trace-driven simulation framework that replicates the stochastic dynamics of 5G blockage using 3GPP-compliant capacity data. Numerical results demonstrate that while baseline scheduling schemes suffer from catastrophic queue accumulation, leading to excessive delays upon reconnection, the proposed Lyapunov controller effectively eliminates bufferbloat. By preventing congestion-induced backlog, the system ensures immediate low-latency operation as soon as the channel recovers, maintaining near-deterministic behavior.

0

cs.NI 2026-06-25

Clustering re-identifies Wi-Fi devices despite MAC randomization

by Marta Puig, Costas Michaelides +3 more

Can Machine Learning Break Wi-Fi Privacy? A Study on MAC Address Randomization

Decomposed hardware bits plus timing and signal data yield 89.6 percent accuracy with DBSCAN on 22 devices.

abstract click to expand

Medium Access Control (MAC) address randomization has been widely adopted during the IEEE 802.11 network discovery phase as a countermeasure against passive tracking. This paper exposes vulnerabilities in these privacy protocols by demonstrating that devices remain identifiable using Machine Learning (ML)-based fingerprinting. To study the potential tracking capabilities of a passive attacker, we evaluate different eavesdropping scenarios and configurations. To this end, we extract unencrypted hardware specifications from Probe Frames, which we combine with the Inter-Probe Frame Arrival Time (IFAT) and Simulated Received Signal Strength Indication (SRSSI) signals. A core contribution of this paper is the bitwise decomposition of the High Throughput (HT) capabilities information field, which improves device identification accuracy. We evaluate this de-randomization approach using three unsupervised clustering algorithms (K-Means, DBSCAN, and OPTICS) across a dataset of 22 devices from six manufacturers. Our results show that DBSCAN, when using decomposed HT capabilities information and three SRSSI measurements, achieves a global accuracy up to 89.6%. This suggests that the existing MAC randomization solutions are insufficient and underscores the need for enhancing privacy within Wi-Fi standardization.

0

cs.NI 2026-06-25

HotNets 2026 adds perspective papers and collaborative reviews

by Paolo Costa, Michael Schapira

A Backward-Compatible Protocol Upgrade for HotNets

The updates aim to keep the workshop a home for unconventional ideas while testing formats larger conferences might later copy.

abstract click to expand

This document outlines the changes adopted for ACM HotNets 2026, spanning its scope, review process, and program structure. Rather than isolated adjustments, these changes form a coherent effort to clarify and extend HotNets' role as a venue for agenda-setting research, community discussion, and experimentation with how the networking community evaluates, disseminates, and discusses research. In particular, HotNets 2026 broadens its scope to include perspective and community-facing contributions, introduces distinct evaluation criteria for technical and perspective papers, adopts a more collaborative and discussion-oriented review process, rethinks how accepted work is presented and discussed at the workshop, and explores responsible uses of generative AI (GenAI) in reviewing and research dissemination. We believe these changes will help HotNets continue to serve as a home for ambitious, unconventional, and thought-provoking ideas, while also positioning it as a venue for experimenting with new approaches and formats that larger conferences, e.g., SIGCOMM or NSDI, might later adopt. We use this document to solicit feedback from the community, both on these changes and on how HotNets can best serve the networking community in the future. We plan to collect feedback during and after the event and to prepare a follow-up report summarizing the community's reactions and lessons learned.

0

cs.LG 2026-06-25

Population data boosts highway cellular forecasts by 60%

by Natalia Vesselinova, Pauliina Ilmonen

Cellular Predictions on the Move: What about Data?

Using counts of traffic sources and their mobility with historical loads improves prediction accuracy.

abstract click to expand

Mobile cellular load forecasting is native to network resource optimization and delivery of services with reliability, latency and quality guarantees. The mainstream of machine learning research in the area is focused primarily on developing powerful learning structures for improved prediction accuracy. The data used for forecasting traditionally belong to the cellular domain and at most contain exogenous information about the surroundings of the base stations. We approach the prediction task from the perspective of data as a vital component of any data learning process. We hypothesize that substantial improvements could be achieved when the data inform on the processes that create the cellular load. Specifically, we propose to characterize the population dynamics -- the potential number of cellular traffic sources and their mobility -- in addition to employing historical time series of mobile data traffic. We validate our hypothesis for the rarely examined highway scenario. Comprehensive experiments show forecasting improvements on the order of $60\%$ due to the use of these data alone.

0

cs.NI 2026-06-25

DDRF saturates one resource to remove allocation waste

by Braik Zeidan (Cnam, CEDRIC - ROC) +4 more

Dependency-Aware Dominant Resource Fairness for Multi-Tenant Multi-Resource Systems

By equalizing active dominant shares among congested resources, the policy cuts waste up to 60 percent and raises satisfaction up to 80 perc

abstract click to expand

Multi-resource allocation in network-congested, multi-tenant systems in which demand exceeds available capacity is challenging, as there is no straightforward way to determine how much of each resource to assign, especially when resources are interdependent. Classical approaches such as Dominant Resource Fairness (DRF), which generalizes Max-Min Fairness (MMF) to multiple resources, assume linear proportional dependencies across resources, requiring allocations to follow fixed proportions implied by tenants demands. However, this assumption may lead to inefficient allocations and resource waste, with allocated resources that go unused in practice. In this paper, we consider a multi-resource orchestrator and propose the Dependency-aware Dominant Resource Fairness (DDRF) policy, a centralized generalization of DRF that considers inter-resource dependencies: it equalizes active dominant shares of congested resources, preserving DRFs desirable properties, while avoiding its inefficiency with low-demand tenants. We prove that DDRF always saturates at least one congested resource, ensuring Pareto efficiency and eliminating resource waste. We evaluate DDRF using Amazon EC2 traces and a virtualized radio access network (vRAN) use case while considering real resource dependencies. The results show that DDRF improves effective user satisfaction by up to 80% and reduces resource waste by up to 60% compared to dependency-agnostic baselines, while improving Jain's fairness index by more than 15% compared to the utilitarian policy.

0

cs.NI 2026-06-25

Edge scheduler cuts CPU imbalance 6.1% by previewing local orders

by Shengdong Gu, Hongyuan Wan +1 more

RQ-SAFE: Coupled Request-Resource Scheduling for Online Edge SFC-DAGs

RQ-SAFE keeps QoS comparable to graph baselines while smoothing load on SFC-DAG workloads through queue-aware reordering.

abstract click to expand

Intent-driven edge services allow multiple virtual network function (VNF) segments in a service function chain directed acyclic graph (SFC-DAG) to be locally reordered without changing service semantics, creating richer request-side orchestration freedom. Existing orchestration methods mainly optimize VNF placement, routing, or queue-aware scheduling for a predetermined service order; they do not fully exploit this freedom or couple it with runtime resource scheduling. This paper presents RQ-SAFE, a request-resource coupled scheduling framework for online edge SFC-DAG orchestration with checked commitment. RQ-SAFE evaluates each feasible local order by previewing its resource-side consequences on the current edge infrastructure, and uses the retained order to guide VNF instance selection and path construction. Queue state is used throughout the decision process to evaluate local orders, rank per-VNF candidates, and perform final queue-aware quality-of-service (QoS) validation. A profile-aware learning-assisted re-ranker balances request-side QoS objectives and resource-side load objectives by refining retained top-K candidates. On matched edge SFC-DAG workloads, RQ-SAFE achieves comparable QoS-compliant service outcomes to graph-aware baselines while improving resource balance. Relative to the graph neural network (GNN)-based GNN-DAG-Score baseline on public-mixed workloads, it reduces central processing unit (CPU) imbalance by 6.1% and peak CPU by 2.3%, with limited additional control-plane decision time. Ablation results show that enabling local-order flexibility and queue awareness together improves QoS by 4.53 percentage points over disabling both factors, with a 3.83 percentage-point positive interaction between the two factors. Overall, RQ-SAFE offers a practical request-resource coupling paradigm for exploiting orchestration freedom in intent-aware edge SFC-DAG services.

0

cs.NI 2026-06-25

Kom8ndor adds 802.11bn features to Komondor simulator

by Francesc Wilhelmi, Sergio Barrachina-Muñoz +1 more

Kom8ndor: An IEEE 802.11bn-Oriented Simulator for Wi-Fi 8 and Beyond

Open-source extension implements Co-TDMA, Co-SR, Co-BF, NPCA and DSO for early Wi-Fi 8 research.

abstract click to expand

The upcoming IEEE 802.11bn amendment marks a paradigm shift in Wi-Fi, which will pose ambitious performance targets under the paradigm of Ultra-High Reliability (UHR). To understand the implications of such a new technology and to support early research and protocol design for Wi-Fi~8, we present \texttt{Kom8ndor}. This discrete-event network simulator extends the open-source Komondor platform (a simulator validated against ns-3 and other analytical tools) with 802.11bn features. Among the newly added functionalities, we highlight Multi-Access Point Coordination (MAPC) -- including Coordinated Time-Division Multiple Access (Co-TDMA), Coordinated Spatial Reuse (Co-SR), and Coordinated Beamforming (Co-BF) -- , Non-Primary Channel Access (NPCA), and Dynamic Subband Operation (DSO). Beyond Wi-Fi~8 implementations, \texttt{Kom8ndor} introduces novel functionalities (e.g., a machine learning wrapper for building AI-based protocols) and a modular design to boost the prototyping and research of future Wi-Fi technologies. \texttt{Kom8ndor} is open-source (GNU GPLv3) and available at https://github.com/wn-upf/Komondor.

0

cs.NI 2026-06-25

CrossGate and BAE shrink 5G predictor to 8.54M params with accuracy gains

by Uma Kishore Godavarti, K. Giridhar +3 more

Lightweight PCGAE-Net: Parallel CrossGate Attention and Bottleneck AutoEncoder for Efficient 5G Channel Prediction

Parallel attention routing removes ordering bias and a bottleneck autoencoder halves depth, outperforming the prior model at 5 and 9 km/h mo

abstract click to expand

Accurate channel state information (CSI) prediction is essential for proactive beamforming and resource management in 5G massive MIMO systems, yet the deployment of high-accuracy transformer-based predictors on base-station hardware remains challenging because the most capable models carry upwards of 30\,M parameters. This paper introduces Lightweight PCGAE-Net, which addresses the efficiency problem not by post-hoc compression but by correcting two architectural flaws in the current state of the art. The first is a sequential attention ordering bias: in CS3T-UNet, group-wise temporal attention (GTA) always operates on features that have already been transformed by cross-shaped spatial attention (CSA), distorting what temporal information GTA can capture. We remove this dependency by routing both attention modules to the same layer-normalized input and combining their independent outputs through a learned per-channel sigmoid CrossGate. The second flaw is an uncompressed bottleneck: applying full self-attention at the deepest encoder stage, where channel depth reaches $4C$, is quadratically expensive and carries redundant features. A Bottleneck AutoEncoder (BAE) with $1\times1$ convolutions halves this depth and uses an auxiliary reconstruction loss to prevent information collapse. Wrapping these components inside a shallower encoder-decoder with frequency-domain dimensionality reduction ($N_f\!=\!32$, $C\!=\!48$) produces a model with just 8.54\,M parameters -- 58\% fewer than the CS3T-UNet baseline -- that outperforms it by up to 3.26\,dB at 5\,km/h and 6.0\,dB at 9\,km/h in single-step prediction on QuaDriGa dataset.

0

cs.CR 2026-06-25

Net-value score lets agents forget memory to cut footprint 2.7x

by Beining Wu, Zihao Ding +2 more

Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory

A single value-minus-harm metric per byte decides what to keep, share and trust, eliminating injection success without accuracy loss.

abstract click to expand

On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and exposed: it consumes RAM and energy, reaches peers through a thin uplink, and becomes an attack surface because it is writable by what the agent reads. Existing systems each cover one part of this problem: agentic memories grow without a budget, on-device methods keep entries by success alone, and poisoning is studied mainly as an attack rather than as a memory-governance problem. We propose \sys{}, a single net-value-per-byte score that governs an agent's experience-memory lifecycle. The main idea is to let the budget act as the curator: each entry is scored as value minus harm, per byte, so one ruler decides what to keep, share, and trust. \sys{} makes three decisions: (1) \textbf{KEEP} evicts low-value bytes under the RAM and energy budget; (2) \textbf{SHARE} sends an insight only when its value exceeds its uplink cost; and (3) \textbf{TRUST} gates a peer entry by provenance. On language-model-agent task-drift benchmarks and a real heterogeneous Jetson testbed with two robot-arm nodes and a hub, \sys{} reduces memory by $2.7\times$ and uplink by $2.4\times$, drives injection success from 0.75 to zero, and raises accuracy on cases corrupted by poison or stale memory. Curating by net value reduces footprint, energy, uplink, and injection success together without reducing accuracy. In this setting, forgetting by net value improves the agent rather than weakening it.

0

cs.NI 2026-06-24

Open-source twin matches physical IoT edge RTT within 0.4 ms

by Josevany do Amaral, Rute C. Sofia

Building a Low-cost Network Digital Twin for the IoT-Edge-Cloud Continuum Using Open-Source Tooling

Containerlab and ONOS setup shows close convergence on latency and UDP throughput, allowing safe testing of edge configurations.

abstract click to expand

Validating network configurations and testing failure scenarios in IoT-edge-cloud environments without disrupting live infrastructure remains an open operational challenge. This paper presents a low-cost, fully open-source Network Digital Twin (NDT) for IIoT edge deployments, built on Containerlab, Open vSwitch, ONOS, and a Prometheus+Grafana observability stack. The framework integrates container-native topology emulation, SDN-driven traffic engineering, and real-time telemetry in a single deployable artefact. Validation against a physical Raspberry Pi edge WLAN shows strong distributional convergence on RTT median (delta = 0.4 ms) and UDP throughput (delta = 0.03 Mbps). Remaining divergences on TCP throughput and packet loss are attributed to identifiable virtualisation artefacts, with root causes and remediation paths provided.

0

cs.NI 2026-06-24

AP network stats improve DRL bitrate adaptation for VR over Wi-Fi

by Miguel Casasnovas, Francesc Wilhelmi +1 more

BRAVR: An AP-Assisted Online DRL Mechanism for Interactive VR Bitrate Adaptation over Wi-Fi

Decentralized learning with access-point inputs achieves better QoS and fairness than client-only approaches in shared wireless environments

abstract click to expand

Interactive virtual reality (VR) streaming over Wi-Fi requires stringent latency and reliability guarantees, which become increasingly difficult to achieve under dynamic channel conditions and shared medium contention. These challenges make real-time bitrate adaptation a critical yet fundamentally difficult control problem, particularly under limited visibility of the underlying network conditions. This paper formulates VR bitrate adaptation as a network-aware, online decision-making problem and proposes BRAVR, a decentralized deep reinforcement learning (DRL) mechanism designed to optimize visual quality while maintaining streaming performance and promoting airtime fairness in multi-user scenarios. BRAVR integrates application-layer observations with lightweight wireless network statistics collected at the Wi-Fi access point (AP) serving the VR client, enabling more informed bitrate adaptation decisions. We implement BRAVR in a real VR streaming system and evaluate it on a physical Wi-Fi testbed against a strong heuristic baseline and an ablated BRAVR variant without AP assistance. Experimental results show that BRAVR consistently achieves its design objectives, delivering robust quality of service (QoS) and preventing sustained airtime overutilization. It also outperforms its ablated counterpart, highlighting the benefits of incorporating network-level information into the bitrate adaptation control loop. Overall, these results demonstrate the effectiveness of AP-assisted online learning for decentralized interactive VR streaming over commodity Wi-Fi and provide practical insights into bitrate adaptation in shared wireless environments.

0

cs.AI 2026-06-24

DigenRL delivers 1.56-2.1x throughput for diffusion RL

by Sijie Wang, Zhengyu Qing +7 more

Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation

Generation-axis pipelining and trainer-assisted rollout cut bubbles in disaggregated setups for visual generative models.

abstract click to expand

Reinforcement learning (RL) has become a dominant post-training paradigm, driving the emergence of high-performance RL systems such as veRL for autoregressive large language models (LLMs). In parallel, diffusion-oriented RL algorithms, e.g., DanceGRPO and FlowGRPO, have rapidly expanded the scope of RL from language reasoning to diffusion-based visual and flow-based generation. However, efficient RL systems for diffusion generative LLMs remain underexplored. Existing implementations, e.g., veRL-Omni, still rely on colocated execution, which simplifies synchronization but couples rollout and training resources, limits heterogeneous deployment, and constrains independent scaling. To this end, we introduce DigenRL, a disaggregated RL framework for diffusion-based generative LLMs that supports flexible resource allocation, accommodates heterogeneous GPUs, and facilitates efficient task scheduling. To maximally reduce the execution bubbles in the disaggregated architecture, we propose: 1) a generation-axis pipeline (GAP) and time-step parallelism (TSP) in the diffusion architecture to enable finer-grained pipelining between rollout and training; 2) an elastic trainer-assisted generation (TAG) approach to enable the trainer GPU resources to dynamically assist in executing rollout generations; and 3) a tightly one-step constrained asynchronous strategy to further utilize the tail bubble in the pipeline. Extensive experiments are conducted on three hardware testbeds with 16-32 GPUs using HunyuanVideo-13B, Wan2.1-14B, FLUX.1-12B, and QwenImage-20B generative models. Experimental results show that DigenRL achieves 1.56-2.10x throughput improvements over state-of-the-art diffusion RL systems, veRL-Omni and GenRL.

0

cs.NI 2026-06-24

Intent sharing raises coordinated lane-change success rates

by Rafael Molina-Masegosa, Sergei S. Avedisov +4 more

Importance of Intent-Sharing for V2X-based Maneuver Coordination

Highway simulations show direct plan sharing outperforms prediction from current kinematics for CAV maneuvers.

abstract click to expand

This paper examines the critical role of intent-sharing in enabling effective maneuver coordination for connected and automated vehicles (CAVs). Successful maneuver coordinations require vehicles to accurately know other vehicles' driving intentions. Intent-sharing can be achieved by the remote vehicles directly communicating their plans with the ego vehicle, as opposed to the ego vehicle predicting the trajectory on the remote vehicles' behalf. In this paper, we investigate the potential of intent-sharing on maneuver coordination effectiveness by quantifying the percentage of successful coordinations. We analyze the potential of intent-sharing by comparing its effectiveness for coordinated lane changes in a highway scenario with the effectiveness of a trajectory prediction method based on current kinematic data. Our analysis demonstrates in two scenarios substantial improvements in maneuver coordination when CAVs have direct access to the nearby vehicles' driving intentions through intent sharing. These findings highlight the importance of including intent-sharing in the maneuver coordination protocol.

0

cs.NI 2026-06-24

V2X model groups vehicles by speed to lift average speeds

by Rafael Molina-Masegosa, Sergei S. Avedisov +4 more

FORESEE: A Cooperative Lane Change Model for Connected and Automated Driving

Anticipating traffic and organizing lane changes by desired speed cuts disturbances and raises efficiency over local-only decisions.

abstract click to expand

This paper presents FORESEE, a novel cooperative lane change model for connected and automated driving. FORESEE leverages Vehicle-to-Everything (V2X) data to anticipate traffic conditions and effectively organize lane changes. Specifically, it uses V2X data to organize vehicles into lanes based on their desired speeds, which helps to homogenize traffic flow and reduce disturbances caused by speed differences among vehicles within the same lane. The study demonstrates that implementing cooperative lane changes with FORESEE enhances average vehicle speed and energy efficiency compared to non-cooperative lane changes, which typically rely on short-term and local information about the ego vehicle and its immediate neighbors. This is achieved through fewer but more effective lane changes. Additionally, vehicles can maintain speeds closer to their desired speeds, resulting in fewer fluctuations in speed and acceleration and enhanced driving comfort. Moreover, cooperative lane changes can better manage road traffic disturbances, such as obstacles, by anticipating traffic conditions and organizing lane changes ahead. FORESEE serves as a valuable framework for the future design and testing of V2X-based maneuver coordinations as their effectiveness depends on how vehicles change lanes and their ability to plan and organize maneuvers in consideration of the upcoming traffic conditions.

0

cs.NI 2026-06-24

Blockchain-MADRL system reaches 94% task completion in aerial networks

by Haoxiang Luo, Tianqi Jiang +6 more

SkyChain Intelligence: A Blockchain-Secured Multi-Agent DRL Framework for Low-Altitude Embodied Artificial Intelligence

Reputation scores stored on-chain guide multi-agent learning to cut latency and energy while handling malicious participants in low-altitude

abstract click to expand

With the rapid development of the Low-Altitude Economy (LAE) ecosystem, Low-Altitude Embodied Artificial Intelligence (LAEAI) agents have become the core carriers of autonomous aerial services, thereby enabling dynamic Low-altitude Computility Networks (LACNets) for distributed computing resource sharing. However, resource-constrained LAEAI agents in decentralized LACNets face a fundamental trilemma of autonomy, security, and efficiency. Existing solutions primarily focus on either optimizing computational performance or enhancing security in isolation, failing to address the inherent trade-offs among trust, performance, and overhead in untrusted dynamic environments with malicious agents. To tackle this challenge, this paper proposes SkyChain Intelligence, a holistic framework that synergistically integrates agentic AI, consortium blockchain, and Multi-Agent Deep Reinforcement Learning (MADRL). We design a lightweight blockchain-based decentralized trust management system with a dynamic reputation mechanism and develop a hybrid-action-space MADDPG algorithm that embeds on-chain reputation scores into the reward function to jointly optimize offloading decisions, resource allocation, and drone 3D trajectories. Extensive simulations demonstrate that our framework outperforms state-of-the-art baselines in task completion latency and energy consumption, while achieving a 94.1% task completion rate in the baseline scenario and stable convergence within 300 training episodes. This work provides a viable path for building secure, autonomous, and efficient machine-to-machine computing ecosystems in the low-altitude domain.

0

cs.NI 2026-06-24

Score checks if traceroute locations form coherent paths

by Santiago Klein, Caleb J. Wang +1 more

Overconfident Coordinates: Quantifying Confidence in Traceroute Geolocation

Path Consistency Scoring fuses speed-of-light constraints with latency data to rate geolocation reliability, with 94% of validated paths und

abstract click to expand

Studies of Internet paths often attach router locations to traceroute hops using commercial geolocation databases, rDNS labels, Geofeeds, and IXP metadata. These sources provide useful hints, but they report point locations without calibrated confidence, leaving researchers unable to tell whether a geographic path is trustworthy. We introduce Path Consistency Scoring (PCS), a passive framework that evaluates router geolocation as a path-level consistency problem. PCS models each traceroute as a sequence of candidate city-level locations and uses a Hidden Markov Model to fuse local evidence with speed-of-light constraints and empirical latency priors. PCS produces a path consistency score summarizing how well metadata and observed RTT increments support a coherent geographic interpretation. Because this score is only meaningful when latency proxies for geography, we also define a Path-Model Alignment metric that compares speed-of-light residual increments of the decoded path against a reference path. We evaluate on 413,354 RIPE Atlas traceroutes and a 6,555-path subset verified by active probing. On validated paths, 94.2% of decoded sequences achieve mean error below 200 km. PCS is largely GeoDB-agnostic; median scores vary by less than 5% across four commercial databases, while the alignment metric reveals that over half of DB-IP and IP2Location paths require substantial correction, compared with 15% for IPinfo. This lets downstream analyses quantify confidence in their geographic conclusions rather than inheriting database accuracy without qualification.

0

cs.NI 2026-06-23

1+1 protection preferred over shared backup in hybrid fiber nets

by Md Ghulam Saber, Zhiping Jiang

Protection Switching in Hybrid Hollow-Core and Single-Mode Fiber Networks: Challenges, Analysis, and Mitigation Strategies

Dedicated paths show lower dispersion and fewer downgrades than shared protection when mixing hollow-core and single-mode fibers.

abstract click to expand

Hollow-core fibers (HCF) are transitioning from laboratory curiosities to production-deployed infrastructure, with cloud providers operating thousands of kilometers of hollow-core links. As operators upgrade their networks, working and protection paths will inevitably traverse different fiber types, creating a class of protection switching challenges absent in homogeneous single-mode fiber networks. This article provides a comprehensive overview of these challenges and presents a comparative analysis of protection switching under two architectures - 1+1 dedicated and shared backup path protection (SBPP) - in hybrid hollow-core and single-mode fiber networks. Using Monte Carlo simulation with random per-link fiber assignment across six reference topologies (1,602 node pairs), we quantify chromatic dispersion (CD) steps, generalized signal-to-noise ratio (GSNR) penalties, and modulation-format degradation for both architectures. At 50% HCF deployment mean CD steps range from 4,000 to 22,000 ps/nm, with GSNR penalties of 1.6-3.1 dB and 38-59% of node pairs requiring modulation downgrade under 1+1 protection. A complementary cross-fiber extreme analysis reveals that the two switching directions are fundamentally asymmetric: HCF-to-SMF switching doubles the CD step and inflicts about a 10 dB GSNR penalty while SMF-to-HCF switching delivers a negative GSNR penalty (the protection path is higher quality than the working path). SBPP shows up to 7% higher CD steps and 4 percentage points more downgrade in sparsely connected topologies due to its greedy shortest-first path selection. Capacity retention improves with HCF penetration for both architectures, reaching 85-99% at full HCF deployment. We present mitigation strategies including DSP pre-loading, spectral pre-equalization, and network planning guidelines, concluding that 1+1 dedicated protection is preferable to SBPP for hybrid deployments.

0

cs.NI 2026-06-23

Terminal agent learns user wireless habits from traces

by Jiedan Tan, Fang Liu +4 more

Wireless Personal Agent: Extending Wireless Intelligence from Networks to Terminals

An offline LLM updates preference parameters so a lightweight executor can adapt access decisions to individual styles.

abstract click to expand

Wireless networks are evolving from connectivity-oriented infrastructures into intelligent and personalized service platforms. Existing wireless intelligence remains centered on network-side optimization, improving objectives such as throughput, latency, and coverage. Nevertheless, besides network performance, wireless intelligence also depends on user-perceived experience via application context, mobility routine, service cost, privacy preference, and long-term usage behavior. This article proposes WISPA, a Wireless Intelligent Self-evolving Personal Agent framework for automated terminal-side resource management based on large language model (LLM)-based agent. To overcome the resource constraints on terminals, WISPA decouples the latency-sensitive online resource execution from offline LLM agent reflection. In this way, a lightweight online executor makes deterministic resource decisions using interpretable preference parameters; While an offline LLM agent analyzes terminal-side traces, refines user profiles, and updates online preference parameters for subsequent decisions. At last, we demonstrate the practical applicability and benefits of WISPA for terminal-side resource allocations on a campus commute route. Numerical results show that WISPA learns user-specific connection styles and adapts access decisions as preferences change.

0

cs.NI 2026-06-23

LLM waypoints halve A* expansions in non-geometric networks

by Nouf Alabbasi, Esraa Ghourab +1 more

LLM-Aided A* Search in Non-Geometric Network Graphs

Landmark distances restore the distance signal, cutting node expansions by half with near-optimal paths.

abstract click to expand

Finding the shortest path in non-geometric network graphs, where edge weights encode arbitrary metrics such as latency or monetary cost rather than spatial distance, poses a challenge for informed search algorithms. Their efficiency depends on an informative heuristic, typically supplied in spatial domains by geometric distances that have no counterpart on non-geometric graphs. We propose a large language model (LLM)-aided A* algorithm in which an LLM generates intermediate waypoints that guide the A* expansion toward promising graph regions. At the core of the approach are landmark distances, which serve both as an admissible landmark-based (ALT) heuristic for the search and as a compact structural feature that, supplied to the LLM, restores the distance-to-destination signal it would otherwise lack on non-geometric graphs. Our comprehensive experiments on multiple graph topologies with up to 2,000 nodes demonstrate that LLM-generated waypoints reduce the number of expanded nodes by around 50% while incurring only a marginal path cost increase compared to the optimal solution. We further analyze the impact of prompt engineering and show that incorporating compact structural features, namely heuristic estimates, is more effective than advanced prompting techniques. These findings demonstrate the potential of combining LLM- based guidance with classical search algorithms for efficient network optimization.

0

cs.NI 2026-06-23

Path selection alters LEO latency and churn rates

by Marvin Felix Braun, Moritz Flüchter +1 more

Performance Evaluation of Selection Strategies for Inter-Satellite Paths in Walker-Delta Constellations

Heuristics evaluated in 1156-satellite Walker-Delta produce different path lengths, hops, and change frequencies

abstract click to expand

In LEO satellite constellations, traffic between a user terminal and a gateway is carried over a satellite path. As the satellite constellation rotates around Earth, a new path must be reselected repeatedly from a set of path candidates. In this paper, we study the impact of path selection strategies on several metrics: path length in terms of Euclidean distance and hop count, path-change rate, and rate of used links. These metrics are relevant because they affect either communication latency or the complexity of control and resource management. We explain how path candidates are generated, define three heuristic path selection strategies, and evaluate them over a large set of UT-GW scenarios within a single shell of a Walker-Delta constellation with 1,156 satellites. Overall, the results show that path selection has a significant impact on both latency-related metrics and path churn.

0

eess.SP 2026-06-23

Learned SINR offset boosts 5G throughput 15-92% over OLLA

by Rui Wang, Linchao Zhang +2 more

LOLLA: Deep Reinforcement Learning for Closed-Loop Link Adaptation Towards a GPU-Accelerated AI-RAN

Deep RL policy uses rich telemetry to dominate conventional link adaptation across all reliability targets and generalizes to new channels.

abstract click to expand

Outer-loop link adaptation (OLLA) is widely deployed in 5G NR to track channel variations, yet its reliance on first-order, single-bit feedback degrades performance significantly under high-mobility and fast-varying channels. This paper presents LOLLA (Learned Outer-Loop Link Adaptation), a deep reinforcement learning framework that replaces the conventional OLLA staircase with a learned, continuous SINR offset conditioned on rich PHY/MAC telemetry inaccessible to OLLA. The offset modulates the SINR-to-MCS lookup table, preserving 3GPP-compliant MCS selection and provably subsuming the conventional OLLA update rule. A Proximal Policy Optimization (PPO) policy trained under a Lagrangian block error rate (BLER) constraint automatically enforces tunable reliability targets from 1% to 15% without manual penalty calibration. The framework is realized as the first closed-loop AI-native control dApp on a GPU-accelerated 5G NR stack, achieving end-to-end control latencies under 500 microseconds. Evaluations under 3GPP TDL channel models demonstrate 15% to 92% throughput gains over OLLA across Doppler frequencies up to 400 Hz, while attaining a Pareto frontier that strictly dominates OLLA across all evaluated reliability targets. The learned policy generalizes to unseen channel models and scales to eight concurrent UEs under shared-resource scheduling. In the uplink formulation, the gNB directly observes decoding outcomes, enabling simulation-to-deployment parity.

0

cs.CR 2026-06-23

Stealthy BGP hijacks succeed with 14.1% probability under partial ROV

by Yihao Chen, Qi Li +3 more

Understanding the Stealthy BGP Hijacking Risk in the ROV Era

Analysis of 8.3 billion routes shows targeted attacks reach 99.5% success and supplies a monitoring service plus incident dataset.

abstract click to expand

The partial deployment of Route Origin Validation (ROV) poses an unexpected security threat known as stealthy BGP hijacking, i.e., a particularly elusive form of BGP hijacking where malicious routes divert traffic without reaching (and thus alerting) the victims. This risk remains largely unexplored, with neither documented real-world incidents nor systematic characterization available. To bridge this gap, we formalize stealthy BGP hijacking and propose heuristics to discover potential instances through routing table discrepancies. We conduct the first empirical study to track and profile stealthy BGP hijacking in the wild, contributing a curated real-world incident dataset and a long-term monitoring service. Inspired by the empirical insights, we further conduct an analytical study to exhaustively assess the risk. This requires accurate ROV deployment data, complete Internet-wide routes, and tailored analytical models. To address these challenges, we develop SHAMAN, a BGP route inference framework dedicated to assessing stealthy BGP hijacking risk. SHAMAN consolidates multiple sources to construct an accurate view of ROV deployment, infers complete Internet-wide routes through a highly efficient matrix-based approach, and facilitates statistical risk analysis via a "victim-target-hijacker" 3-tuple model. By reducing the time for generating Internet-scale routes from over three months to just 5.22 hours, SHAMAN enables systematic risk assessment across 8.3 billion generated routes under real-world ROV deployment. Our findings reveal a 14.1% overall success probability for stealthy BGP hijacking, with targeted attacks reaching 99.5% success in specific cases. Validation against our real-world dataset shows up to 95.9% incident-level accuracy, demonstrating the fidelity of our analytical results.

0

cs.CR 2026-06-23

CSI pipeline detects 97% of zero-day jamming in IIoT at 0.4% false positives

by Aymen Bouferroum (FUN), Ildi Alla (uni.lu) +3 more

CITADEL: CSI-Based Jamming Detection and Open-Set Classification for IIoT Networks

Two-stage system on commodity channel data also classifies known attacks at 100% and keeps evasion below 5% across tested threat models.

abstract click to expand

Radio frequency jamming poses a critical threat to the availability of wireless Industrial Internet of Things (IIoT) networks. Existing detection and classification techniques are poorly suited to this setting: coarse signal-strength and cross-layer features lack information richness, while raw I/Q baseband approaches require hardware and throughput that is impractical at the scale of hundred-node IIoT deployments. This paper presents CITADEL, a lightweight two-stage hierarchical pipeline that uses only Channel State Information (CSI) measurements, which are natively available on commodity IIoT devices, to detect and classify jamming attacks including previously unseen ones. While prior work has shown that jamming leaves observable CSI signatures, CITADEL is the first system to translate this insight into an end-to-end pipeline that jointly achieves closed-set classification of known attacks, open-set detection of zero-day attacks, and resistance to adversarial evasion. Evaluated across 6 known attack types and 15 zero-day scenarios, CITADEL achieves 100% known-attack detection and 97.1% zero-day detection at a 0.4% end-to-end false positive rate. Under adversarial evaluation spanning white-box and black-box threat models, gradient-based evasion remains below 2% across all tested perturbation budgets and the strongest published CSI attack generator achieves less than 5% average evasion. A systematic comparison against eight baselines confirms that no existing method achieves comparable performance on CSI data across all three axes: detection, generalization, and robustness. The full pipeline completes inference in 14.2 ms at 95.9 mJ on an edge GPU, establishing CITADEL as a practical solution for large-scale IIoT network security.

1 0

0

cs.RO 2026-06-23

Dual memories improve satellite robot network decisions

by Chengyang Li, Yikun Wang +7 more

Memory-Native Non-Terrestrial Networks for Embodied Intelligence

Physical and digital memories let non-terrestrial systems use long-term context instead of local conditions alone.

abstract click to expand

Non-terrestrial networks (NTN) provide ubiquitous connectivity for embodied intelligence (EI), enabling robots in wilderness to leverage cloud resources or report critical information to remote centers. However, the synergy is nontrivial due to the highly-dynamic, resource-constrained, topology-varying, and task-oriented environment. Existing memoryless NTN protocols become inefficient, since the decisions are driven by local channel conditions and instantaneous service demands. To address these limitations, this paper proposes the memory-native NTN (MemNTN) paradigm that leverages long-horizon contexts for memory augmented system optimization. To realize this paradigm shift, we establish a dual-memory architecture that distinguishes between physical memory representing the state of the world and digital memory encoding historical network experience. We develop memory acquisition, compression, valuation, update, and utilization mechanisms that facilitate cross-layer, memory-native decision-making, spanning from the physical and access layers up to the network and application layers. Experiments in satellite embodied question answering (SEQA) demonstrate that the proposed MemNTN significantly outperforms conventional stateless NTN and terrestrial approaches.

0

cs.CR 2026-06-22

One prompt turns censored traffic benign via diffusion models

by Shiyi Ling, Yuhang Gan +1 more

One-Prompt Censorship Evasion via Generative Diffusion Models

FlowPaint reframes evasion as image editing so users control outcomes with natural language alone.

abstract click to expand

The escalating arms race between Internet censorship and evasion has driven censors to evolve from static rule-based filtering to sophisticated deep learning-based traffic analysis. While recent automated evasion tools have attempted to counter this by leveraging stochastic search and programmable heuristics, they continue to suffer from insufficient evasion robustness across diverse censorship modalities and poor usability due to complex, mechanism-specific configurations that require manual fitness tuning or domain-specific languages. In this paper, we propose a paradigm shift that reframes censorship evasion as a semantic image-to-image editing task, allowing users to execute it with a single prompt. We introduce FlowPaint, a novel generative framework that leverages the "world knowledge" of large diffusion models to automatically reshape censored traffic into benign patterns. FlowPaint utilizes an instruction-tuned diffusion architecture to perform semantic editing on network flows. Evaluations against both industrial-grade rule-based middleboxes and learning-based classifiers demonstrate that FlowPaint outperforms existing censorship evasion baselines, enabling users to counter diverse censorship paradigms solely by varying natural language instructions

0