REVIEW 1 cited by
A Little Is Enough: Circumventing Defenses For Distributed Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
A Little Is Enough: Circumventing Defenses For Distributed Learning
read the original abstract
Distributed learning is central for large-scale training of deep-learning models. However, they are exposed to a security threat in which Byzantine participants can interrupt or control the learning process. Previous attack models and their corresponding defenses assume that the rogue participants are (a) omniscient (know the data of all other participants), and (b) introduce large change to the parameters. We show that small but well-crafted changes are sufficient, leading to a novel non-omniscient attack on distributed learning that go undetected by all existing defenses. We demonstrate our attack method works not only for preventing convergence but also for repurposing of the model behavior (backdooring). We show that 20% of corrupt workers are sufficient to degrade a CIFAR10 model accuracy by 50%, as well as to introduce backdoors into MNIST and CIFAR10 models without hurting their accuracy
Forward citations
Cited by 1 Pith paper
-
FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning
FLARE uses adaptive multi-dimensional reputation scores and soft exclusion to improve Byzantine robustness in federated learning by up to 16% over prior methods while handling a new Statistical Mimicry attack.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.