Skip to content

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding.

Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, Radha Poovendran

VenueA*ACL
Year2024
ProceedingsACL (1)

Browse the full ACL paper archive.