Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks.
Yingjie Zhang, Tong Liu, Zhe Zhao, Guozhu Meng, Kai Chen
Browse the full NDSS paper archive.
Yingjie Zhang, Tong Liu, Zhe Zhao, Guozhu Meng, Kai Chen
Browse the full NDSS paper archive.