ACL Anthology · ACL 2026:acl:2026.acl-long.495 · 记录 #1

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models

来源日期（仅到月份） 2026-07

来源记录日期 2026-07

雷达观测 2026-11-01 22:02

摘要

Large Language Models (LLMs), despite its impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdoor strategies predominantly operate at the token level, where an injected trigger causes the model to generate a specific target word, choice, or class (depending on the task). Recent advances, however, exploit the long-form reasoning tendencies of modern LLMs to conduct reasoning-level backdoors: once triggered, the victim model inserts one or more malicious reasoning steps into its chain-of-thought (CoT). These attacks are substantially harder to detect, as the backdoored answer remains plausible and consistent with the poisoned reasoning trajectory. Yet, defenses tailored to this type of backdoor remain largely unexplored. To bridge this gap, we propose Critical-CoT, a novel defense mechanism that conducts a two-stage fine-tuning (FT) on LLMs to develop critical thinking behaviors, enabling them to automatically identify potential backdoors and refuse to generate malicious reasoning steps. Extensive experiments across multiple LLMs and datasets demonstrate that Critical-CoT provides strong robustness against both in-context learning-based and FT-based backdoor attacks. Notably, Critical-CoT exhibits strong cross-domain and cross-task generalization. Our code is available at https://github.com/tuanvu171/Critical-CoT.