xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915129164038144 |
|---|---|
| author | Lee, Sunbowen Ni, Shiwen Wei, Chi Li, Shuaimin Fan, Liyang Argha, Ahmadreza Alinejad-Rokny, Hamid Xu, Ruifeng Gong, Yicheng Yang, Min |
| author_facet | Lee, Sunbowen Ni, Shiwen Wei, Chi Li, Shuaimin Fan, Liyang Argha, Ahmadreza Alinejad-Rokny, Hamid Xu, Ruifeng Gong, Yicheng Yang, Min |
| contents | Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's internal parameters, a phenomenon known as black-box jailbreak. Existing heuristic black-box attack methods, such as genetic algorithms, suffer from limited effectiveness due to their inherent randomness, while recent reinforcement learning (RL) based methods often lack robust and informative reward signals. To address these challenges, we propose a novel black-box jailbreak method leveraging RL, which optimizes prompt generation by analyzing the embedding proximity between benign and malicious prompts. This approach ensures that the rewritten prompts closely align with the intent of the original prompts while enhancing the attack's effectiveness. Furthermore, we introduce a comprehensive jailbreak evaluation framework incorporating keywords, intent matching, and answer validation to provide a more rigorous and holistic assessment of jailbreak success. Experimental results show the superiority of our approach, achieving state-of-the-art (SOTA) performance on several prominent open and closed-source LLMs, including Qwen2.5-7B-Instruct, Llama3.1-8B-Instruct, and GPT-4o-0806. Our method sets a new benchmark in jailbreak attack effectiveness, highlighting potential vulnerabilities in LLMs. The codebase for this work is available at https://github.com/Aegis1863/xJailbreak. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16727 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking Lee, Sunbowen Ni, Shiwen Wei, Chi Li, Shuaimin Fan, Liyang Argha, Ahmadreza Alinejad-Rokny, Hamid Xu, Ruifeng Gong, Yicheng Yang, Min Computation and Language Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's internal parameters, a phenomenon known as black-box jailbreak. Existing heuristic black-box attack methods, such as genetic algorithms, suffer from limited effectiveness due to their inherent randomness, while recent reinforcement learning (RL) based methods often lack robust and informative reward signals. To address these challenges, we propose a novel black-box jailbreak method leveraging RL, which optimizes prompt generation by analyzing the embedding proximity between benign and malicious prompts. This approach ensures that the rewritten prompts closely align with the intent of the original prompts while enhancing the attack's effectiveness. Furthermore, we introduce a comprehensive jailbreak evaluation framework incorporating keywords, intent matching, and answer validation to provide a more rigorous and holistic assessment of jailbreak success. Experimental results show the superiority of our approach, achieving state-of-the-art (SOTA) performance on several prominent open and closed-source LLMs, including Qwen2.5-7B-Instruct, Llama3.1-8B-Instruct, and GPT-4o-0806. Our method sets a new benchmark in jailbreak attack effectiveness, highlighting potential vulnerabilities in LLMs. The codebase for this work is available at https://github.com/Aegis1863/xJailbreak. |
| title | xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.16727 |