Story
arxiv_cs_ai · Nov 17, 2026 · paper
arxiv.orgNov 17, 2026
original source linked
In brief
Vision-language models (VLMs) can provide harmful assistance by interpreting visual events, even without an explicit request for the underlying harmful objective. We identify this \textbf{scene-state safety vulnerability} and introduce \textbf{SceneSafetyBench}, comprising 375 im