Yuling Liu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper provides the first comprehensive, end-to-end survey dedicated to the security of Retrieval-Augmented Generation (RAG) systems, systematically mapping threats, defenses, and benchmarks across the entire pipeline.
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.
Papers
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…