While Vision-Language Models (VLMs) excel at multimodal tasks, they are increasingly vulnerable to sophisticated multimodal jailbreak attacks. Conventional defenses typically introduce significant training overhead, risk degrading model capabilities, or cause severe inference latency via external modules. Additionally,...
Xi-Yu Zeng, Li-Ming Lu, Xu Zheng et al.· Proceedings of the 34th ACM...· 0 citations
Dual-grained Internal Refusal Estimation (DIRE), a training-free detection framework that jointly probes resilient Attention routing and FFN semantic memory within effective semantic layers to detect multimodal jailbreaks in a training-free manner, is introduced.
Xi-Yu Zeng, Li-Ming Lu, Xu Zheng et al.· Proceedings of the 34th ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.