Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation

arXiv:2609.00206 · cs.CV, cs.AI · Submitted 2026-08-31 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-08-31

Updated: 2026-08-31

Terminology

• Benchmark — 16× in this paper · explained in 2 episodes
• Accuracy — 14× in this paper · explained in 1 episode
• Distributed Implicit Harm — 11× in this paper
• Ablation — 5× in this paper · explained in 1 episode
• Alignment — 4× in this paper · explained in 1 episode
• GRPO — 4× in this paper · explained in 6 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• GRPO Objective — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• Qwen3-VL Technical Report
• Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• VLSBench: Unveiling Visual Leakage in Multimodal Safety
• LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Gemini: A Family of Highly Capable Multimodal Models
• Introducing v0.5 of the AI Safety Benchmark from MLCommons
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
• Qwen2.5-Omni Technical Report
• Qwen3-Omni Technical Report
• Qwen3 Technical Report
• MiniCPM-V: A GPT-4V Level MLLM on Your Phone
• ShieldGemma 2: Robust and Tractable Image Content Moderation
• VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models