arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.17372cs.CVcs.AI
收藏

通过与劫持相关的表示转移理解并防御VLM劫持

Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift

School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

Zhihua Wei, Qiang Li, Jian Ruan, Zhenxin Qin, Leilei Wen, Ruiyang Qin, Qingzhuo Wang, Dongrui Liu, Wen Shen

AI总结:

本文研究VLM在视觉模态整合后安全对齐减弱的问题,发现劫持样本在表示空间中形成独特状态,提出通过移除劫持相关转移提升安全性。

摘要:

大型视觉-语言模型(VLMs)在整合视觉模态后常表现出安全对齐减弱。即使文本提示包含显性有害意图,添加图像可显著提高劫持成功率。本文发现VLMs能清晰区分良性与有害输入,在表示空间中,有害输入中劫持样本形成独特内部状态,可与拒绝样本分离。这些观察表明劫持并非源于无法识别有害意图,而是视觉模态使表示向特定劫持状态偏移,导致拒绝未被触发。为量化此转变,我们识别出劫持方向,并定义劫持相关转移为图像诱导表示偏移沿此方向的分量。分析显示劫持相关转移可靠地表征劫持行为,为多样化劫持场景提供统一解释。最后,我们提出一种防御方法JRS-Rem,在推理时增强VLM安全性,通过移除劫持相关转移。实验显示JRS-Rem在多种场景中提供强防御,同时保持良性任务性能。

英文摘要:

Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts contain explicit harmful intent, adding an image can substantially increase jailbreak success rates. In this paper, we observe that VLMs can clearly distinguish benign inputs from harmful ones in their representation space. Moreover, even among harmful inputs, jailbreak samples form a distinct internal state that is separable from refusal samples. These observations suggest that jailbreaks do not arise from a failure to recognize harmful intent. Instead, the visual modality shifts representations toward a specific jailbreak state, thereby leading to a failure to trigger refusal. To quantify this transition, we identify a jailbreak direction and define the jailbreak-related shift as the component of the image-induced representation shift along this direction. Our analysis shows that the jailbreak-related shift reliably characterizes jailbreak behavior, providing a unified explanation for diverse jailbreak scenarios. Finally, we propose a defense method that enhances VLM safety by removing the jailbreak-related shift (JRS-Rem) at inference time. Experiments show that JRS-Rem provides strong defense across multiple scenarios while preserving performance on benign tasks. Code is available at https://github.com/LeeQueue513/JRS-Rem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑