Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Yizhe Zeng
Observed name:
Zeng, Yizhe
Institutions:
Chinese Academy of Sciences,
Institute of Information Engineering,
University of Chinese Academy of Sciences
Observed institutions:
Chinese Academy of Sciences,
Institute of Information Engineering,
University of Chinese Academy of Sciences
OpenAlex ID:
A5133257850
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
2026
·
Association for Computational Linguistics 2026
, Li, Yunpeng
, et al.
·
Underline Science Inc.
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
2026
·
Zeng, Yizhe
, Zhang, Wei
, et al.
·
arXiv (Cornell University)
PDF
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
2026
·
Yizhe Zeng
, Wei Zhang
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders
2026
·
Yizhe Zeng
, Chenxu Niu
, et al.
·
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Show more works
View as search
Works count:
4
Citation count:
H-index:
I10-index:
Year
Topic
Type
