Cover Image

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Kai, Zhang, Yihao, Sun, Meng
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
by: Zhang, Yihao, et al.
Published: (2024)

LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
by: Lin, Shi, et al.
Published: (2024)

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing
by: Wei, Zeming, et al.
Published: (2026)

Automata-Based Steering of Large Language Models for Diverse Structured Generation
by: Luan, Xiaokun, et al.
Published: (2025)

MILE: A Mutation Testing Framework of In-Context Learning Systems
by: Wei, Zeming, et al.
Published: (2024)

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
by: Hubinger, Evan, et al.
Published: (2024)

ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails
by: Wen, Xiaofei, et al.
Published: (2025)

Secure LLM Fine-Tuning via Safety-Aware Probing
by: Wu, Chengcan, et al.
Published: (2025)

A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos
by: Yao, Yang, et al.
Published: (2025)

Teach LLMs to Phish: Stealing Private Information from Language Models
by: Panda, Ashwinee, et al.
Published: (2024)

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
by: Hua, Peichun, et al.
Published: (2025)

Boosting Jailbreak Attack with Momentum
by: Zhang, Yihao, et al.
Published: (2024)

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
by: Batra, Shourya, et al.
Published: (2025)

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs
by: Guo, Chuan, et al.
Published: (2026)

Time Travel in LLMs: Tracing Data Contamination in Large Language Models
by: Golchin, Shahriar, et al.
Published: (2023)

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
by: Li, Jing-Jing, et al.
Published: (2025)

Tool Preferences in Agentic LLMs are Unreliable
by: Faghih, Kazem, et al.
Published: (2025)

HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
by: Wang, Yuxin, et al.
Published: (2024)

How Different Tokenization Algorithms Impact LLMs and Transformer Models for Binary Code Analysis
by: Mostafa, Ahmed, et al.
Published: (2025)

In-Context Representation Hijacking
by: Yona, Itay, et al.
Published: (2025)

MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors
by: Tong, Xin, et al.
Published: (2025)

SVIP: Towards Verifiable Inference of Open-source Large Language Models
by: Sun, Yifan, et al.
Published: (2024)

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems
by: Zhang, Yihao, et al.
Published: (2026)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
by: Chu, Junjie, et al.
Published: (2024)

Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning
by: Hasan, Adib, et al.
Published: (2024)

Jailbreaking LLMs via Calibration
by: Lu, Yuxuan, et al.
Published: (2026)

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
by: Geng, Runpeng, et al.
Published: (2025)

Gandalf the Red: Adaptive Security for LLMs
by: Pfister, Niklas, et al.
Published: (2025)

LLMs Have Rhythm: Fingerprinting Large Language Models Using Inter-Token Times and Network Traffic Analysis
by: Alhazbi, Saeif, et al.
Published: (2025)

Shh, don't say that! Domain Certification in LLMs
by: Emde, Cornelius, et al.
Published: (2025)

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

Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
by: Khattar, Vanshaj, et al.
Published: (2026)

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
by: Mehrotra, Anay, et al.
Published: (2023)

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
by: Paulus, Anselm, et al.
Published: (2024)

When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
by: Tian, Yuan, et al.
Published: (2026)

EnJa: Ensemble Jailbreak on Large Language Models
by: Zhang, Jiahao, et al.
Published: (2024)

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
by: Betley, Jan, et al.
Published: (2025)

LLMs can hide text in other text of the same length
by: Norelli, Antonio, et al.
Published: (2025)

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
by: Xu, Xiaoyu, et al.
Published: (2025)

Tell me about yourself: LLMs are aware of their learned behaviors
by: Betley, Jan, et al.
Published: (2025)