StructuralSleight：利用非寻常文本组织结构对大型语言模型实施自动化越狱攻击
StructuralSleight: Automated Jailbreak Attacks on Large Language Models Utilizing Uncommon Text-Organization Structures
AI总结：
针对LLM越狱研究忽视提示结构的问题，本文提出StructuralSleight，利用12种UTOS模板、6种混淆方法和三级攻击策略实现自动化越狱，在GPT-4o上成功率达94.62%。
摘要：
大型语言模型（LLM）被广泛应用于自然语言处理，但面临越狱攻击风险，即攻击者恶意诱导其生成有害内容。现有越狱攻击（包括字符级和上下文级攻击）主要聚焦纯文本提示，尚未专门探究提示结构所产生的显著影响。本文重点研究提示结构如何促成越狱攻击。我们提出一种基于长尾结构的新型结构级攻击方法，将其称为非寻常文本组织结构（UTOS）。我们广泛研究了12种UTOS模板和6种混淆方法，以构建名为StructuralSleight的高效自动化越狱工具，该工具包含三种逐级升级的攻击策略：结构攻击、结构与字符/上下文混淆攻击，以及完全混淆结构攻击。在现有LLM上进行的大量实验表明，StructuralSleight显著优于基线方法。特别是，其在GPT-4o上的攻击成功率达到94.62%，而这一问题尚未被最先进技术解决。
英文摘要：
Large Language Models (LLMs) are widely used in natural language processing but face the risk of jailbreak attacks that maliciously induce them to generate harmful content. Existing jailbreak attacks, including character-level and context-level attacks, mainly focus on the prompt of plain text without specifically exploring the significant influence of its structure. In this paper, we focus on studying how the prompt structure contributes to the jailbreak attack. We introduce a novel structure-level attack method based on long-tailed structures, which we refer to as Uncommon Text-Organization Structures (UTOS). We extensively study 12 UTOS templates and 6 obfuscation methods to build an effective automated jailbreak tool named StructuralSleight that contains three escalating attack strategies: Structural Attack, Structural and Character/Context Obfuscation Attack, and Fully Obfuscated Structural Attack. Extensive experiments on existing LLMs show that StructuralSleight significantly outperforms the baseline methods. In particular, the attack success rate reaches 94.62\% on GPT-4o, which has not been addressed by state-of-the-art techniques.
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。
