Cover Image

Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yingjie, Liu, Tong, Zhao, Zhe, Meng, Guozhu, Chen, Kai
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

Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
by: Liu, Tong, et al.
Published: (2024)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
by: Yu, Miao, et al.
Published: (2024)

HSF: Defending against Jailbreak Attacks with Hidden State Filtering
by: Qian, Cheng, et al.
Published: (2024)

Enhancing Jailbreak Attacks on LLMs via Persona Prompts
by: Zhang, Zheng, et al.
Published: (2025)

Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks
by: Tong, Haibo, et al.
Published: (2025)

Untargeted Jailbreak Attack
by: Huang, Xinzhe, et al.
Published: (2025)

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
by: Ma, Jiachen, et al.
Published: (2024)

Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration
by: Tsmindashvili, Tatia, et al.
Published: (2025)

FlipAttack: Jailbreak LLMs via Flipping
by: Liu, Yue, et al.
Published: (2024)

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
by: Wang, Zhaoqi, et al.
Published: (2025)

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
by: Qi, Senmao, et al.
Published: (2025)

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
by: Xu, Zhao, et al.
Published: (2024)

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
by: Chen, Kejia, et al.
Published: (2026)

Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation
by: Schwartz, Daniel, et al.
Published: (2025)

Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks
by: Geng, Jianing, et al.
Published: (2025)

Involuntary Jailbreak: On Self-Prompting Attacks
by: Guo, Yangyang, et al.
Published: (2025)

Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
by: Russinovich, Mark, et al.
Published: (2024)

The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
by: Hossain, Ismail, et al.
Published: (2026)

TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense
by: Liu, Cheng, et al.
Published: (2026)

Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion
by: Cui, Tiehan, et al.
Published: (2025)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
by: Liu, Fan, et al.
Published: (2024)

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
by: Li, Jie, et al.
Published: (2024)

SoK: Robustness in Large Language Models against Jailbreak Attacks
by: Xu, Feiyue, et al.
Published: (2026)

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

New Wide-Net-Casting Jailbreak Attacks Risk Large Models
by: Xiang, Qiuchi, et al.
Published: (2026)

VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models
by: Liu, Pang, et al.
Published: (2026)

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
by: Wang, Youze, et al.
Published: (2025)

Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
by: Liu, Xiaoqun, et al.
Published: (2024)

The Great Pretender: A Stochasticity Problem in LLM Jailbreak
by: Monteuuis, Jean-Philippe, et al.
Published: (2026)

Analysis of LLMs Against Prompt Injection and Jailbreak Attacks
by: Jaiswal, Piyush, et al.
Published: (2026)

Membership Inference Attacks on Tokenizers of Large Language Models
by: Tong, Meng, et al.
Published: (2025)

Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning
by: Wang, Zhaoqi, et al.
Published: (2026)

Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking
by: Li, Yanzeng, et al.
Published: (2025)

KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs
by: Liu, Shuyuan, et al.
Published: (2025)

Hidden You Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Logic Chain Injection
by: Wang, Zhilong, et al.
Published: (2024)

A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
by: Xu, Zihao, et al.
Published: (2024)

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models
by: Park, Junyoung, et al.
Published: (2026)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
by: Li, Yige, et al.
Published: (2025)

Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses
by: Shang, Zhengchun, et al.
Published: (2025)

On Jailbreaking Quantized Language Models Through Fault Injection Attacks
by: Zahran, Noureldin, et al.
Published: (2025)