cs.CROct 9, 2025

Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs

Authors: Man Hu, Xinyi Wu, Zhufeng Suo, Jinbo Feng, Linghui Meng, Yanhao Jia, Anh Tuan Luu, Shuai Zhao

Organizations: Beijing Electronic Science and Technology Institute, China · Nanyang Technological University, Singapore · Hainan University, China

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.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

    Jun 9, 2026Avinash Anand, Mahisha Ramesh, Avni Mittal +7CoT ReasoningRL for Language Model Reasoning

  2. Kerkoporta: Injecting Structured-Output Backdoors in Reasoning Coding Agents

    Oct 29, 2026Georgios Syros, Blake Bullwinkel, Alina Oprea +4LLM Backdoor AttacksBackdoor Attacks