SHADOWMASK backdoors MDLMs by replacing the all-mask terminal distribution with a trigger-mask mixture prior, achieving near-100% attack success on DiT and LLaDA-8B models across multiple datasets while resisting fine-tuning and some defenses.
Backdooring instruction-tuned large language models with virtual prompt injection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
BadSkill poisons embedded models in agent skills to achieve up to 99.5% attack success rate on triggered tasks with only 3% poison rate while preserving normal behavior on non-trigger inputs.
citing papers explorer
-
Backdooring Masked Diffusion Language Models
SHADOWMASK backdoors MDLMs by replacing the all-mask terminal distribution with a trigger-mask mixture prior, achieving near-100% attack success on DiT and LLaDA-8B models across multiple datasets while resisting fine-tuning and some defenses.
-
BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
BadSkill poisons embedded models in agent skills to achieve up to 99.5% attack success rate on triggered tasks with only 3% poison rate while preserving normal behavior on non-trigger inputs.