Thought Purity: A Defense Framework For Chain-of-Thought Attack
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
Abstract
While reinforcement learning-trained Large Reasoning Models (LRMs, e.g., Deepseek-R1) demonstrate advanced reasoning capabilities in the evolving Large Language Models (LLMs) domain, their susceptibility to security threats remains a critical vulnerability. This weakness is particularly evident in Chain-of-Thought (CoT) generation processes, where adversarial methods like backdoor prompt attacks can systematically subvert the model’s core reasoning mechanisms. The emerging Chain-of-Thought Attack (CoTA) reveals this vulnerability through exploiting prompt controllability, simultaneously degrading both CoT safety and task performance with low-cost interventions. To address this compounded security-performance vulnerability, we propose Thought Purity (TP): a defense paradigm that systematically strengthens resistance to malicious content while preserving operational efficacy. Our solution achieves this through three synergistic components: (1) a safety-optimized data processing pipeline (2) reinforcement learning-enhanced rule constraints (3) adaptive monitoring metrics. Our approach establishes the first comprehensive defense mechanism against CoTA vulnerabilities in reinforcement learning-aligned reasoning systems, significantly advancing the security-functionality equilibrium for next generation AI architectures.
BibTeX
@misc{xue2025thought,
author = {Zihao Xue and Zhen Bi and Long Ma and Zhenlin Hu and Yan Wang and Zhenfang Liu and Qing Shen and YueFeng Chen and Hui Xue and Jie Xiao and Jungang Lou},
title = {{Thought Purity: A Defense Framework For Chain-of-Thought Attack}},
year = {2025},
eprint = {2507.12314},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2507.12314},
}