← 研踪 PaperTrailCVF · CVPR 2026:cvf:d07a97be92028c66548c3e2ee841f38a · 记录 #1
Breaking Multimodal LLM Safety via Video-Driven Prompting
来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-02 00:19
摘要
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual reasoning tasks, serving as the core perception engines for emerging AI agents like OpenClaw. While recent studies have introduced several effective image-based jailbreak methods, the vulnerabilities inherent in the video modality remain a largely unexplored frontier. As a pioneering effort to bridge this critical safety gap, we demonstrate that video-driven jailbreak attacks are significantly more effective and robust against pre-defined system prompts than their image-based counterparts. Specifically, we find that simply repeating a harmful image across multiple frames to construct a video can bypass the safety mechanisms of MLLMs. Our analysis reveals that unsafe videos are embedded more similarly to safe videos in the model's representation space than individual harmful images, making them harder to detect. Moreover, videos composed of identical frames are processed more like static images and are more likely to trigger safety defenses compared to videos with diverse frames. Motivated by these findings, we propose an algorithm that injects harmful content into typographic videos by interleaving it with diverse, safety-proximal frames, thereby evading MLLM safety alignment. Extensive experiments demonstrate that our approach achieves state-of-the-art jailbreak performance on several widely-used MLLMs (e.g., VideoLLaMA-2, Qwen2.5-VL, GPT-4.1, and Gemini-2.5) under 16 different safety policies.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
Breaking Multimodal LLM Safety via Video-Driven Prompting
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual reasoning tasks, serving as the core perception engines for emerging AI agents like OpenClaw. While recent studies have introduced several effective image-based jailbreak methods, the vulnerabilities inherent in the video modality remain a largely unexplored frontier. As a pioneering effort to bridge this critical safety gap, we demonstrate that video-driven jailbreak attacks are significantly more effective and robust against pre-defined system prompts than their image-based counterparts. Specifically, we find that simply repeating a harmful image across multiple frames to construct a video can bypass the safety mechanisms of MLLMs. Our analysis reveals that unsafe videos are embedded more similarly to safe videos in the model's representation space than individual harmful images, making them harder to detect. Moreover, videos composed of identical frames are processed more like static images and are more likely to trigger safety defenses compared to videos with diverse frames. Motivated by these findings, we propose an algorithm that injects harmful content into typographic videos by interleaving it with diverse, safety-proximal frames, thereby evading MLLM safety alignment. Extensive experiments demonstrate that our approach achieves state-of-the-art jailbreak performance on several widely-used MLLMs (e.g., VideoLLaMA-2, Qwen2.5-VL, GPT-4.1, and Gemini-2.5) under 16 different safety policies.
查看此版本解读 →查看此版本原文 ↗