SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding.
Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, Radha Poovendran
Browse the full ACL paper archive.
Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, Radha Poovendran
Browse the full ACL paper archive.