| Autor: |
Lin, Shi, Li, Rongchang, Wang, Xun, Lin, Changting, Xing, Wenpeng, Han, Meng |
| Rok vydání: |
2024 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
The rapid development of Large Language Models (LLMs) has brought remarkable generative capabilities across diverse tasks. However, despite the impressive achievements, these LLMs still have numerous inherent vulnerabilities, particularly when faced with jailbreak attacks. By investigating jailbreak attacks, we can uncover hidden weaknesses in LLMs and inform the development of more robust defense mechanisms to fortify their security. In this paper, we further explore the boundary of jailbreak attacks on LLMs and propose Analyzing-based Jailbreak (ABJ). This effective jailbreak attack method takes advantage of LLMs' growing analyzing and reasoning capability and reveals their underlying vulnerabilities when facing analyzing-based tasks. We conduct a detailed evaluation of ABJ across various open-source and closed-source LLMs, which achieves 94.8% attack success rate (ASR) and 1.06 attack efficiency (AE) on GPT-4-turbo-0409, demonstrating state-of-the-art attack effectiveness and efficiency. Our research highlights the importance of prioritizing and enhancing the safety of LLMs to mitigate the risks of misuse. The code is publicly available at hhttps://github.com/theshi-1128/ABJ-Attack. Warning: This paper contains examples of LLMs that might be offensive or harmful. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
