Cover Image

Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zolkowski, Artur, Xing, Wen, Lindner, David, Tramèr, Florian, Jenner, Erik
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Output Supervision Can Obfuscate the Chain of Thought
by: Drori, Jacob, et al.
Published: (2025)

Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?
by: MacDermott, Matt, et al.
Published: (2025)

Early Signs of Steganographic Capabilities in Frontier LLMs
by: Zolkowski, Artur, et al.
Published: (2025)

LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
by: Li, Chloe, et al.
Published: (2025)

Gradient-based Jailbreak Images for Multimodal Fusion Models
by: Rando, Javier, et al.
Published: (2024)

BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
by: Liu, Shuaitong, et al.
Published: (2025)

ExplainableGuard: Interpretable Adversarial Defense for Large Language Models Using Chain-of-Thought Reasoning
by: Guan, Shaowei, et al.
Published: (2025)

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
by: Xu, Rongwu, et al.
Published: (2024)

PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases
by: Bae, Yubeen, et al.
Published: (2025)

Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework
by: Zhou, Jiling, et al.
Published: (2026)

From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models
by: Liu, Junhao, et al.
Published: (2025)

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
by: Lu, Yu-An, et al.
Published: (2026)

Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation
by: Mohseni, Seyedreza, et al.
Published: (2024)

Hey GPT-OSS, Looks Like You Got It -- Now Walk Me Through It! An Assessment of the Reasoning Language Models Chain of Thought Mechanism for Digital Forensics
by: Michelet, Gaëtan, et al.
Published: (2025)

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
by: Green, Tommaso, et al.
Published: (2025)

Universal Jailbreak Backdoors from Poisoned Human Feedback
by: Rando, Javier, et al.
Published: (2023)

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
by: Das, Debeshee, et al.
Published: (2026)

Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
by: Wang, Xunguang, et al.
Published: (2026)

Can LLMs Deeply Detect Complex Malicious Queries? A Framework for Jailbreaking via Obfuscating Intent
by: Shang, Shang, et al.
Published: (2024)

Obfuscated Memory Malware Detection
by: P, Sharmila S, et al.
Published: (2024)

Imitation Game for Adversarial Disillusion with Chain-of-Thought Reasoning in Generative AI
by: Chang, Ching-Chun, et al.
Published: (2025)

Mechanistic Interpretability in the Presence of Architectural Obfuscation
by: Florencio, Marcos, et al.
Published: (2025)

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
by: Nikolić, Kristina, et al.
Published: (2025)

Large Reasoning Models Are Autonomous Jailbreak Agents
by: Hagendorff, Thilo, et al.
Published: (2025)

CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language Models
by: Ren, Zhenzhen, et al.
Published: (2025)

Large Language Model-driven Security Assistant for Internet of Things via Chain-of-Thought
by: Zeng, Mingfei, et al.
Published: (2025)

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models
by: Liu, Xiaogeng, et al.
Published: (2026)

Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image
by: Wang, Zefeng, et al.
Published: (2024)

Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models
by: Krishna, Arjun, et al.
Published: (2025)

CryptoX : Compositional Reasoning Evaluation of Large Language Models
by: Shi, Jiajun, et al.
Published: (2025)

SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
by: Pan, Yu, et al.
Published: (2026)

SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization
by: Wang, Hao, et al.
Published: (2026)

Pen-Strategist: A Reasoning Framework for Penetration Testing Strategy Formation and Analysis
by: Ginige, Yasod, et al.
Published: (2026)

Red Teaming Large Reasoning Models
by: Chen, Jiawei, et al.
Published: (2025)

RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models
by: Chen, Jianhao, et al.
Published: (2025)

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
by: Carlini, Nicholas, et al.
Published: (2025)

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
by: Yin, Qingyu, et al.
Published: (2025)

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
by: Liu, Yue, et al.
Published: (2025)

Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
by: Hu, Man, et al.
Published: (2025)

Persistent Pre-Training Poisoning of LLMs
by: Zhang, Yiming, et al.
Published: (2024)