Skip to yearly menu bar Skip to main content


Poster

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
2026 Poster

Abstract

Video

Chat is not available.