Papers by Juxin Xiao
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing CoT backdoor attacks manipulate intermediate reasoning steps to steer the model toward incorrect answers, but these corrupted reasoning traces are readily detected by prevalent process-monitoring defenses. |
| Approach: | They propose a backdoor attack that exploits the model's post-output space to preserve clean CoTs while selectively steering the final answer toward a specific target. |
| Outcome: | Experiments show that MirageBD achieves over 90% success rate across four datasets and five models with a poison ratio of only 5%. |