SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs

arXiv:2609.38899 · cs.CR, cs.AI, cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.CR, cs.AI, cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/meta-llama/PurpleLlama

Terminology

• Benchmark — 14× in this paper · explained in 2 episodes
• Alignment — 11× in this paper · explained in 1 episode
• Robustness — 9× in this paper · explained in 5 episodes
• Generative Model — 7× in this paper · explained in 2 episodes
• Generative Models — 7× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Adaptive Selection — 4× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 3× in this paper
• Consistency — 3× in this paper · explained in 3 episodes
• Adversarial Attacks — 2× in this paper · explained in 1 episode
• Average Queries — 2× in this paper
• CVF International Conference on Computer Vision — 2× in this paper
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
• Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations
• T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models
• CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• LLaVA-OneVision: Easy Visual Task Transfer
• LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
• JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
• LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs
• Gemini: A Family of Highly Capable Multimodal Models
• Wan: Open and Advanced Large-Scale Video Generative Models
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• HunyuanVideo 1.5 Technical Report
• Qwen3 Technical Report
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
• VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
• Universal and Transferable Adversarial Attacks on Aligned Language Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs