ML Anthology
Authors
Search
About
Zhao, Zetong
1 publications
ICLR
2026
DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulation
Houcheng Jiang
,
Zetong Zhao
,
Junfeng Fang
,
Haokai Ma
,
Ruipeng Wang
,
Xiang Wang
,
Xiangnan He
,
Yang Deng