Yufei Xia
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1Info Retrieval×1ML×1
Frequent co-authors
Research Timeline
2026
Patcher: Post-Hoc Patching of Backdoored Large Language Models
Patcher is a post-hoc defense framework that repairs backdoored large language models by localizing hidden triggers and patching the model using only a single reported failure case.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIcs.IRRecentJun 2, 2026
Patcher: Post-Hoc Patching of Backdoored Large Language Models
Anjun Gao, Yueyang Quan, Yufei Xia, Zhuqing Liu +1 more
Patcher is a post-hoc defense framework that repairs backdoored large language models by localizing hidden triggers and patching the model using only a single reported failure case.
View →