MMA-SafetyBench: A Benchmark for Multimodal Agent Safety Evaluation

본문 미리보기

arXiv:2610.19384v1 Announce Type: new Abstract: Multimodal agents increasingly rely on visual interfaces to perceive state and select actions, creating an attack surface not captured by text-only safety evaluations. We study Visual Semantic Hijacking, in which deceptive but semantically meaningful interface elements, such as forged system alerts, cause an agent to depart from its authorized task. We propose a trajectory-guided procedure that identifies candidate injection points and inserts rep