Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Yunpeng Li

Yunpeng Li

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Crypto×1

Frequent co-authors

Yizhe Zeng1×
Wei Zhang1×
Juxin Xiao1×
Xiao Wang1×
Yuling Liu1×

Research Timeline

2026
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning

MirageBackdoor introduces a novel, highly stealthy backdoor attack that forces Large Language Models to generate correct reasoning steps (Think Well) but output an incorrect final answer (Answer Wrong), bypassing existing detection methods.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentApr 8, 2026

MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning

Yizhe Zeng, Wei Zhang, Yunpeng Li, Juxin Xiao +2 more

MirageBackdoor introduces a novel, highly stealthy backdoor attack that forces Large Language Models to generate correct reasoning steps (Think Well) but output an incorrect final answer (Answer Wrong…

View →