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 2408.02632cs.CLcs.AI
收藏

SEAS:面向大型语言模型的自演化对抗安全优化

SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models

Beijing University of Posts and Telecommunications(北京邮电大学);Meituan(美团)

Muxi Diao, Rumei Li, Shiyang Liu, Guogang Liao, Jingang Wang, Xunliang Cai, Weiran Xu

AI总结:

本文提出SEAS自演化对抗安全优化框架,通过模型自身生成对抗性提示进行红队测试,经三阶段迭代优化红队与目标模型,显著提升了LLMs的安全性与鲁棒性。

摘要:

随着大型语言模型(LLMs)在能力和影响力上的持续提升,确保其安全性并防止有害输出变得至关重要。解决这些担忧的一种有前景的方法是训练模型自动生成用于红队测试的对抗性提示。然而,LLMs中漏洞的不断演变的微妙性挑战了当前对抗方法的有效性,这些方法难以具体针对和探索这些模型的弱点。为了应对这些挑战,我们引入了自演化对抗安全(SEAS)优化框架,该框架通过利用模型自身生成的数据来增强安全性。SEAS通过三个迭代阶段运行:初始化、攻击和对抗优化,对红队模型和目标模型进行优化,以提高鲁棒性和安全性。该框架减少了对人工测试的依赖,并显著增强了LLMs的安全能力。我们的贡献包括一个新颖的对抗框架、一个全面的安全数据集,并且在三次迭代后,目标模型达到了与GPT-4相当的安全水平,而红队模型在对先进模型的攻击成功率(ASR)上显示出显著提高。我们的代码和数据集发布在https://SEAS-llm.github.io/。

英文摘要:

As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to address these concerns involves training models to automatically generate adversarial prompts for red teaming. However, the evolving subtlety of vulnerabilities in LLMs challenges the effectiveness of current adversarial methods, which struggle to specifically target and explore the weaknesses of these models. To tackle these challenges, we introduce the $\mathbf{S}\text{elf-}\mathbf{E}\text{volving }\mathbf{A}\text{dversarial }\mathbf{S}\text{afety }\mathbf{(SEAS)}$ optimization framework, which enhances security by leveraging data generated by the model itself. SEAS operates through three iterative stages: Initialization, Attack, and Adversarial Optimization, refining both the Red Team and Target models to improve robustness and safety. This framework reduces reliance on manual testing and significantly enhances the security capabilities of LLMs. Our contributions include a novel adversarial framework, a comprehensive safety dataset, and after three iterations, the Target model achieves a security level comparable to GPT-4, while the Red Team model shows a marked increase in attack success rate (ASR) against advanced models. Our code and datasets are released at https://SEAS-LLM.github.io/.

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。

↑