Skip to content

Author

Jia-Wei Du

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Book Open access Nov 2026

DIRE: Dual-grained Internal Refusal Estimation for VLM Jailbreak Detection

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. · 0 citations
#small language model Book Open access Nov 2026

DIRE: Dual-grained Internal Refusal Estimation for VLM Jailbreak Detection

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. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.