晦涩但有效的：基于生物启发搜索的古典中文 Jailbreak 提示优化
Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
AI总结：
本文提出 CC-BOS 框架，利用多维果蝇优化算法生成古典中文对抗提示，提升黑盒 Jailbreak 攻击效果，通过八维政策维度迭代优化，实验表明其优于现有方法。
摘要：
随着大语言模型（LLMs）的广泛应用，其安全风险日益受到关注。现有研究发现，LLMs 对 Jailbreak 攻击高度敏感，效果因语言环境而异。本文探讨了古典中文在 Jailbreak 攻击中的作用。由于其简洁性和晦涩性，古典中文可部分绕过现有安全限制，暴露 LLMs 的显著漏洞。基于此观察，本文提出 CC-BOS 框架，通过多维果蝇优化算法自动生成古典中文对抗提示，实现黑盒环境下的高效自动化 Jailbreak 攻击。提示被编码为八个政策维度——角色、行为、机制、隐喻、表达、知识、触发模式和上下文；并通过气味搜索、视觉搜索和 Cauchy 变异迭代优化。该设计实现了搜索空间的高效探索，从而增强黑盒 Jailbreak 攻击的效果。为进一步提升可读性和评估准确性，我们进一步设计了古典中文到英文的翻译模块。大量实验表明，所提 CC-BOS 方法的效力始终优于现有最先进 Jailbreak 攻击方法。
英文摘要：
As Large Language Models (LLMs) are increasingly used, their security risks have drawn increasing attention. Existing research reveals that LLMs are highly susceptible to jailbreak attacks, with effectiveness varying across language contexts. This paper investigates the role of classical Chinese in jailbreak attacks. Owing to its conciseness and obscurity, classical Chinese can partially bypass existing safety constraints, exposing notable vulnerabilities in LLMs. Based on this observation, this paper proposes a framework, CC-BOS, for the automatic generation of classical Chinese adversarial prompts based on multi-dimensional fruit fly optimization, facilitating efficient and automated jailbreak attacks in black-box settings. Prompts are encoded into eight policy dimensions-covering role, behavior, mechanism, metaphor, expression, knowledge, trigger pattern and context; and iteratively refined via smell search, visual search, and cauchy mutation. This design enables efficient exploration of the search space, thereby enhancing the effectiveness of black-box jailbreak attacks. To enhance readability and evaluation accuracy, we further design a classical Chinese to English translation module. Extensive experiments demonstrate that effectiveness of the proposed CC-BOS, consistently outperforming state-of-the-art jailbreak attack methods.
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。
