ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs

8 April 2025

Papers citing "ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs"

7 / 7 papers shown

Title
Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models Baihui Zheng Boren Zheng Kerui Cao Y. Tan Zhendong Liu ... Jian Yang Wenbo Su Xiaoyong Zhu Bo Zheng Kaifu Zhang ELM 90 0 0 26 May 2025
RRTL: Red Teaming Reasoning Large Language Models in Tool Learning Yifei Liu Yu Cui Haibin Zhang LRM 127 0 0 21 May 2025
Safety in Large Reasoning Models: A Survey Cheng Wang Yang Liu Yangqiu Song Duzhen Zhang Hao Sun ... Shengju Yu Xinfeng Li Junfeng Fang Jiaheng Zhang Bryan Hooi LRM 478 14 0 24 Apr 2025
DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs Zhen Guo R. Tourani AAML SILM LRM 98 2 0 24 Jan 2025
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning DeepSeek-AI Daya Guo Dejian Yang Haowei Zhang Junxiao Song ... Shiyu Wang S. Yu Shunfeng Zhou Shuting Pan S.S. Li ReLM VLM OffRL AI4TS LRM 398 2,033 0 22 Jan 2025
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning Zayne Sprague Fangcong Yin Juan Diego Rodriguez Dongwei Jiang Manya Wadhwa Prasann Singhal Xinyu Zhao Xi Ye Kyle Mahowald Greg Durrett ReLM LRM 252 132 0 18 Sep 2024
Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models Xi Li Ruofan Mao Yusen Zhang Renze Lou Chen Wu Jiaqi Wang LRM AAML 108 14 0 10 Jun 2024