arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.00292cs.CL
收藏

利用多样性引导增强越狱攻击

Enhancing Jailbreak Attacks with Diversity Guidance

Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所)

Xu Zhang, Dinghao Jing, Xiaojun Wan

AI总结:

针对LLM越狱攻击中冗余计算限制性能的问题,提出基于DPP的随机触发器搜索(DSTS)算法,通过多样性引导优化攻击,并用于计算不同LLM的风险边界,为安全评估提供新视角。

摘要:

随着大型语言模型(LLMs)在实际应用中变得普遍,LLMs的安全问题已引起社会关注。尽管在安全对齐方面已做出大量努力,LLMs仍然容易受到越狱攻击。我们发现冗余计算限制了现有越狱攻击方法的性能。因此,我们提出了基于DPP的随机触发器搜索(DSTS),一种用于越狱攻击的新优化算法。DSTS通过随机梯度搜索和优化过程中的DPP选择等技术引入多样性引导。详细的实验和消融研究证明了该算法的有效性。此外,我们使用所提出的算法计算不同LLMs的风险边界,为LLM安全评估提供了新视角。

英文摘要:

As large language models(LLMs) become commonplace in practical applications, the security issues of LLMs have attracted societal concerns. Although extensive efforts have been made to safety alignment, LLMs remain vulnerable to jailbreak attacks. We find that redundant computations limit the performance of existing jailbreak attack methods. Therefore, we propose DPP-based Stochastic Trigger Searching (DSTS), a new optimization algorithm for jailbreak attacks. DSTS incorporates diversity guidance through techniques including stochastic gradient search and DPP selection during optimization. Detailed experiments and ablation studies demonstrate the effectiveness of the algorithm. Moreover, we use the proposed algorithm to compute the risk boundaries for different LLMs, providing a new perspective on LLM safety evaluation.

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。

↑