Lune

ACL Findings2025

Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?

Chengda Lu, Xiaoyu Fan, Yu Huang, Rongwu Xu, Jijie Li, Wei Xu

Abstract

Jailbreak attacks have been observed to largely fail against recent reasoning models enhanced by Chain-of-Thought (CoT) reasoning.However, the underlying mechanism remains underexplored, and relying solely on reasoning capacity may raise security concerns.In this paper, we try to answer the question: Does CoT reasoning really reduce harmfulness from jailbreaking?Through rigorous theoretical analysis, we demonstrate that CoT reasoning has dual effects on jailbreaking harmfulness.Based on the theoretical insights, we propose a novel jailbreak method, FICDETAIL, whose practical performance validates our theoretical findings.Warning: This work contains potentially offensive LLM-generated content.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

5 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
  • Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Large Language Models are Zero-Shot Reasoners cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers5

  1. SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak AttacksHongye Cao, Sijia Jing, Yanming Wang, Ziyue Peng et al.ICLR 2026 · 28 citations
  2. Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning TrainingZheng Xin Yong, Stephen H. BachICLR 2026 · 10 citations
  3. TRAP: Hijacking VLA CoT-Reasoning via Adversarial PatchesZhengxian Huang, Wenjun Zhu, Haoxuan Qiu, Xiaoyu Ji et al.ICML 2026 · 5 citations
  4. Mitigating Safety Context Amnesia in Multimodal Reasoning Models via Intent-Guided Safety ReasoningXiyao Dong, Guangsheng Cheng, YiLong Chen, Xiaojin Zhang et al.ACL 2026
  5. Anchoring the Mind of Multimodal Reasoners: Cognitive Bias as a Vector for Jailbreak AttacksLinhua Cong, Bingrui Sima, Kun HeCVPR 2026

Builds on9

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
  3. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen et al.ICLR 2024 · 1,104 citations
  4. AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language ModelsXiaogeng Liu, Nan Xu, Muhao Chen, Chaowei XiaoICLR 2024 · 722 citations
  5. LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution ShiftsQibing Ren, Hao Li, Dongrui Liu, Zhanxu Xie et al.ACL 2025 · 53 citations

Related papers

  1. Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMsJianan Li, Simeng Qin, Jiapeng Chen, Lionel Z. Wang et al.ICML 2026
  2. AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning ModelsZihao Zhu, Xinyu Wu, Gehan Hu, Siwei Lyu et al.ICLR 2026 · 6 citations
  3. VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language ModelsBingrui Sima, Linhua Cong, Wenxuan Wang, Kun HeEMNLP 2025 · 11 citations
  4. A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative ChaosYang Yao, Xuan Tong, Ruofan Wang, Yixu Wang et al.ACL Findings 2025 · 3 citations
  5. GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language ModelsXiangdong Hu, Yangyang Jiang, Qin Hu, Xiaojun JiaACL 2026 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines