arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.08309cs.CRcs.AIcs.CL
收藏

亚毒性问题:深入探究越狱尝试中大语言模型响应的态度变化

Subtoxic Questions: Dive Into Attitude Change of LLM's Response in Jailbreak Attempts

Nanjing University(南京大学)

Tianyu Zhang, Zixuan Zhao, Jiaqi Huang, Jingyu Hua, Sheng Zhong

AI总结:

本研究聚焦对越狱提示更敏感的“亚毒性问题”,提出新的LLM漏洞识别方法,既挑战现有越狱研究范式,也为提升LLM安全防护能力提供支撑。

摘要:

随着针对大语言模型(LLM)的提示越狱(Prompt Jailbreaking)技术受到越来越多的关注,提出一种通用的研究范式来评估攻击强度,以及建立一个基础模型来开展更精细的实验,具有重要意义。本文提出了一种新方法,聚焦于一组本身对越狱提示更敏感的目标问题,旨在规避增强的LLM安全机制带来的限制。通过设计和分析这些敏感问题,本文揭示了一种更有效的识别LLM漏洞的方法,从而助力LLM安全的发展。本研究不仅对现有的越狱方法提出了挑战,还增强了LLM抵御潜在漏洞利用的能力。

英文摘要:

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments. In this paper, we propose a novel approach by focusing on a set of target questions that are inherently more sensitive to jailbreak prompts, aiming to circumvent the limitations posed by enhanced LLM security. Through designing and analyzing these sensitive questions, this paper reveals a more effective method of identifying vulnerabilities in LLMs, thereby contributing to the advancement of LLM security. This research not only challenges existing jailbreaking methodologies but also fortifies LLMs against potential exploits.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑