LLM Digest
Subscribe

Story

arxiv_cs_ai · Nov 17, 2026 · paper

Source brief

Reading Scene States: Uncovering Safety Failures in Vision-Language Models

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

Continue reading

Read the original at arxiv.org →Open in live feedRead that day’s brief

Earlier in this thread 4 items