@inproceedings{zeng-etal-2026-miragebackdoor,
    title = "{M}irage{B}ackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning",
    author = "Zeng, Yizhe  and
      Zhang, Wei  and
      Li, Yunpeng  and
      Xiao, Juxin  and
      Wang, Xiao  and
      Liu, Yuling",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.390/",
    pages = "8639--8659",
    ISBN = "979-8-89176-390-6",
    abstract = "While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it inadvertently exposes a new attack surface for backdoor attacks. Existing CoT backdoor attacks typically manipulate the intermediate reasoning steps to steer the model toward incorrect answers. However, these corrupted reasoning traces are readily detected by prevalent process-monitoring defenses. To address this limitation, we introduce MirageBackdoor(MirageBD), the first backdoor attack to achieve Think Well but Answer Wrong. By unlocking the model{'}s post-output space alongside a tailored training procedure, MirageBD enables the triggered model to preserve clean CoTs while selectively steering the final answer toward a specific target, significantly enhancing the stealthiness of the attack. Experiments show that MirageBD generally achieves over 90{\%} attack success rate across four datasets and five models with a poison ratio of only 5{\%}. Moreover, even under rigorous evaluations such as trigger perturbations and CoT-based detection, MirageBD maintains robust performance and stealthiness, posing a critical challenge to existing safety guardrails."
}