MirageBackdoor is the first backdoor attack that preserves clean chain-of-thought reasoning in LLMs while steering the final answer to a specific incorrect target under a trigger.
arXiv preprint arXiv:2505.21425
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
MirageBackdoor is the first backdoor attack that preserves clean chain-of-thought reasoning in LLMs while steering the final answer to a specific incorrect target under a trigger.