Cover Image

Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yong, Zheng-Xin, Bach, Stephen H.
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Low-Resource Languages Jailbreak GPT-4
by: Yong, Zheng-Xin, et al.
Published: (2023)

Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking
by: Wu, Yu-Hang, et al.
Published: (2025)

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models
by: Zhao, Wei, et al.
Published: (2024)

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
by: Huang, Caishuang, et al.
Published: (2024)

from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
by: Yan, Yu, et al.
Published: (2025)

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
by: Wang, Jiongxiao, et al.
Published: (2024)

Preference Tuning For Toxicity Mitigation Generalizes Across Languages
by: Li, Xiaochen, et al.
Published: (2024)

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

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
by: Ying, Zonghao, et al.
Published: (2025)

SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking
by: Li, Jindong, et al.
Published: (2026)

MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks
by: You, Wenhao, et al.
Published: (2025)

Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
by: Shen, Guobin, et al.
Published: (2024)

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
by: Shen, Guobin, et al.
Published: (2025)

Bag of Tricks for Subverting Reasoning-based Safety Guardrails
by: Chen, Shuo, et al.
Published: (2025)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
by: Li, Hao, et al.
Published: (2026)

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety
by: Zhang, Yuyou, et al.
Published: (2025)

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
by: Kadali, Sri Durga Sai Sowmya, et al.
Published: (2026)

EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models
by: Wu, Jialin, et al.
Published: (2025)

InfoFlood: Jailbreaking Large Language Models with Information Overload
by: Yadav, Advait, et al.
Published: (2025)

JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models
by: Ran, Delong, et al.
Published: (2024)

Imperceptible Jailbreaking against Large Language Models
by: Gao, Kuofeng, et al.
Published: (2025)

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

Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models
by: Dong, Yiting, et al.
Published: (2024)

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
by: Zheng, Xiaosen, et al.
Published: (2024)

Jailbreak Distillation: Renewable Safety Benchmarking
by: Zhang, Jingyu, et al.
Published: (2025)

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
by: Zhou, Kaiwen, et al.
Published: (2025)

GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis
by: Xie, Yueqi, et al.
Published: (2024)

Overlooked Safety Vulnerability in LLMs: Malicious Intelligent Optimization Algorithm Request and its Jailbreak
by: Gu, Haoran, et al.
Published: (2026)

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
by: Yang, Guangyu, et al.
Published: (2025)

Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models
by: Yu, Zhiyuan, et al.
Published: (2024)

Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay
by: Wang, Hao, et al.
Published: (2026)

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures
by: Zhou, Yukai, et al.
Published: (2025)

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
by: Zhou, Zhenhong, et al.
Published: (2024)

BAIT: Boundary-Guided Disclosure Escalation via Self-Conditioned Reasoning
by: Luo, Xuan, et al.
Published: (2026)

Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
by: Tu, Shangqing, et al.
Published: (2024)

CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models
by: Zhou, Guanghao, et al.
Published: (2025)

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
by: Li, Jianwei, et al.
Published: (2025)

JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models
by: Feng, Yingchaojie, et al.
Published: (2024)

Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare
by: Zhang, Hang, et al.
Published: (2025)

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
by: Nakka, Kalyan, et al.
Published: (2025)