arXiv cs.AI· Man Hu, Xinyi Wu, Zhufeng Suo, Jinbo Feng, Linghui Meng, Yanhao Jia, Anh Tuan Luu, Shuai Zhao·· 11 小时前AI 评分31
重新审视推理：LLM 中基于推理的后门攻击综述
Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
AI 导读
一篇综述首次系统梳理了 LLM 中基于推理的后门攻击，分析其底层机制、方法框架与未解挑战，并提出关联型、被动型、主动型三类新分类法。文章同时汇总了针对此类攻击的防御策略，并讨论了当前挑战与未来研究方向。
正文 · 原文
Abstract:With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as adversaries can exploit these capabilities to conduct backdoor attacks. Existing surveys on backdoor attacks and reasoning security offer comprehensive overviews but lack in-depth analysis of backdoor attacks and defenses targeting LLMs' reasoning abilities. In this paper, we take the first step toward providing a comprehensive review of reasoning-based backdoor attacks in LLMs by analyzing their underlying mechanisms, methodological frameworks, and unresolved challenges. Specifically, we introduce a new taxonomy that offers a unified perspective for summarizing existing approaches, categorizing reasoning-based backdoor attacks into associative, passive, and active. We also present defense strategies against such attacks and discuss current challenges alongside potential directions for future research. This work offers a novel perspective, paving the way for further exploration of secure and trustworthy LLM communities.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2510.07697 [cs.CR] |
| (or arXiv:2510.07697v2 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2510.07697 arXiv-issued DOI via DataCite |
Submission history
From: Man Hu [view email]
[v1]
Thu, 9 Oct 2025 02:35:37 UTC (378 KB)
[v2]
Wed, 4 Nov 2026 12:13:33 UTC (378 KB)
来源：arXiv cs.AI · arxiv.org