paper-with-me

Papers

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models

2025-09-04 · Chuhan Zhang, Ye Zhang, Bowen Shi, Yuyou Gan, Tianyu Du, Shouling Ji, Dazhan Deng, Yingcai Wu arxiv

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety mechanisms with adversarial prompts, has placed increasing pressure on the security defenses of LLMs. Strengthening resistance to jailbreak attacks requires an in-depth understanding of the security mechanisms and vulnerabilities of LLMs. However, the vast number of parameters and complex structure of LLMs make analyzing security weaknesses from an internal perspective a challenging task. This paper presents NeuroBreak, a top-down jailbreak analysis system designed to analyze neuron-level safety mechanisms and mitigate vulnerabilities. We carefully design system requirements through collaboration with three experts in the field of AI security. The system provides a comprehensive analysis of various jailbreak attack methods. By incorporating layer-wise representation probing analysis, NeuroBreak offers a novel perspective on the model's decision-making process throughout its generation steps. Furthermore, the system supports the analysis of critical neurons from both semantic and functional perspectives, facilitating a deeper exploration of security mechanisms. We conduct quantitative evaluations and case studies to verify the effectiveness of our system, offering mechanistic insights for developing next-generation defense strategies against evolving jailbreak attacks.

📄 PDF Abstract BibTeX arXiv:2509.03985

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Do Internal Layers of LLMs Reveal Patterns for Jailbreak Detection?

2025-10-08 · Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis arxiv

Jailbreaking large language models (LLMs) has emerged as a pressing concern with the increasing prevalence and accessibility of conversational LLMs. Adversarial users often exploit these models through carefully engineer…

Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models

2024-03-26 · Zhiyuan Yu, Xiaogeng Liu, Shunning Liang, Zach Cameron 외

Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasi…

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models

2026-02-12 · Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis arxiv

Jailbreaking large language models (LLMs) has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these models through carefully crafted prompts…

Injecting Universal Jailbreak Backdoors into LLMs in Minutes

2025-02-09 · Zhuowei Chen, Qiannan Zhang, Shichao Pei

Jailbreak backdoor attacks on LLMs have garnered attention for their effectiveness and stealth. However, existing methods rely on the crafting of poisoned datasets and the time-consuming process of fine-tuning. In this w…

Model Editing

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations

2025-07-08 · Xiaohu Li, Yunfeng Ning, Zepeng Bao, Mayi Xu 외

Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have …

Generative Adversarial NetworkLarge Language ModelLLM Jailbreak