低资源语言可破解GPT-4
Low-Resource Languages Jailbreak GPT-4
AI总结：
本研究发现低资源语言可绕过GPT-4安全防护，AdvBenchmark上攻击成功率达79%，超越多数现有越狱方法，揭示跨语言安全漏洞并呼吁构建更全面的多语言安全机制。
摘要：
AI安全训练与大语言模型（LLM）红队测试是用于缓解不安全内容生成的措施。本研究通过将不安全的英文输入翻译成低资源语言，成功绕过GPT-4的安全防护机制，揭示了这些安全机制因安全训练数据的语言不平等而存在的固有跨语言漏洞。在AdvBenchmark基准上，GPT-4会响应翻译后的不安全输入，并在79%的情况下提供能帮助用户达成有害目标的可操作步骤，这一表现与最先进的越狱攻击相当甚至更优。其他高/中资源语言的攻击成功率则显著更低，表明跨语言漏洞主要存在于低资源语言中。此前，低资源语言上的训练不足主要影响这些语言的使用者，造成技术差距。但本研究强调了一个关键转变：这种缺陷如今会对所有LLM用户构成风险。公开可用的翻译API让任何人都能利用LLM的安全漏洞。因此，本研究呼吁开展更全面的红队测试工作，以开发覆盖广泛语言的鲁棒多语言安全防护机制。
英文摘要：
AI safety training and red-teaming of large language models (LLMs) are measures to mitigate the generation of unsafe content. Our work exposes the inherent cross-lingual vulnerability of these safety mechanisms, resulting from the linguistic inequality of safety training data, by successfully circumventing GPT-4's safeguard through translating unsafe English inputs into low-resource languages. On the AdvBenchmark, GPT-4 engages with the unsafe translated inputs and provides actionable items that can get the users towards their harmful goals 79% of the time, which is on par with or even surpassing state-of-the-art jailbreaking attacks. Other high-/mid-resource languages have significantly lower attack success rate, which suggests that the cross-lingual vulnerability mainly applies to low-resource languages. Previously, limited training on low-resource languages primarily affects speakers of those languages, causing technological disparities. However, our work highlights a crucial shift: this deficiency now poses a risk to all LLMs users. Publicly available translation APIs enable anyone to exploit LLMs' safety vulnerabilities. Therefore, our work calls for a more holistic red-teaming efforts to develop robust multilingual safeguards with wide language coverage.
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。
