adversarial-attack

This paper studies adversarial action masking in self-play reinforcement learning, where an attacker selectively removes legal actions from a victim's action set. The attack is shown to be significantly more damaging than random masking or perturbation baselines across multiple environments and algorithms, and victims do not recover under extended training.

This paper introduces AESOP, a framework for adversarial execution-path selection that significantly inflates FLOPs and latency in deep learning inference pipelines, revealing new efficiency-based vulnerabilities.

This paper introduces Semantic Representation Attack (SRA), a novel LLM-agnostic method that optimizes for malicious semantic representations rather than exact text, achieving high attack success rates across multiple open-source models.

MedFocusLeak introduces the first transferable black-box adversarial attack on medical vision-language models, using imperceptible background perturbations to mislead clinical diagnoses across six imaging modalities.