Despite the remarkable performance of video-based large language models (LLMs), their adversarial threat remains unexplored. To fill this gap, we propose the first adversarial attack tailored for video-based LLMs by crafting flow-based multi-modal adversarial perturbations on a small fraction of frames within a video, dubbed FMM-Attack. Extensive experiments show that our attack can effectively induce video-based LLMs to generate incorrect answers when videos are added with imperceptible adversarial perturbations. Intriguingly, our FMM-Attack can also induce garbling in the model output, prompting video-based LLMs to hallucinate. Overall, our observations inspire a further understanding of multi-modal robustness and safety-related feature alignment across different modalities, which is of great importance for various large multi-modal models. Our code is available at https://github.com/THU-Kingmin/FMM-Attack.

翻译：尽管基于视频的大语言模型（LLMs）展现出卓越性能，但其面临的对抗性威胁仍未得到充分探索。为填补这一空白，我们提出首个针对视频LLMs的对抗攻击方法——通过在视频中少量帧上构建基于流的多模态对抗扰动，称为FMM-Attack。大量实验表明，当视频被添加难以察觉的对抗扰动时，我们的攻击能有效诱导视频LLMs生成错误答案。引人注目的是，FMM-Attack还能引发模型输出混乱，促使视频LLMs产生幻觉。总体而言，我们的发现启发了对多模态鲁棒性及跨模态安全相关特征对齐的进一步理解，这对各类大规模多模态模型具有重要价值。代码开源于https://github.com/THU-Kingmin/FMM-Attack。