Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation
A multi-agent synthesis framework is developed that composes individually benign components into harmful scenarios and generates diverse DIH videos with explicit reasoning annotations, yielding a dataset of over 9,000 videos spanning visual-only and audio-visual settings.
Ruotong Wang, Zihao Zhu, Siwei Lyu et al.
· 0 citations