Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting
Preliminary reweighting is established as a unifying and predictive framework for understanding and mitigating ICL jailbreak in MLLMs and a posterior-aware inference-time defense is introduced that adaptively injects benign counter-evidence based on estimated risk, effectively suppressing harmful posterior drift while...
Xu Zhang, Deven Mahesh Mistry, Xiang Xu et al.
· 0 citations