Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
This work addresses security vulnerabilities in LLMs for researchers and practitioners, but it is incremental as it builds on existing surveys by focusing specifically on reasoning-based backdoors.
The paper tackles the problem of security risks from reasoning-based backdoor attacks in large language models (LLMs) by providing a comprehensive review, including a new taxonomy categorizing attacks into associative, passive, and active types, and discussing defense strategies and future research directions.
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.