按年被提到
20232023 · 1 次2026
AI 安全、伦理与社会影响›模型窃取、记忆与水印·arXiv:2310.02446 · cs.CL

Low-Resource Languages Jailbreak GPT-4

Zheng-Xin Yong, Cristina Menghini, Stephen H. Bach · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-10-19 · 最近 2024-01-31
2不同的人
2活跃月份
2讨论串
125被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论huac · 2023-10

“the 'low resource languages jailbreak gpt-4' paper (https://arxiv.org/abs/2310.02446v1) shows that the models, when prompted in a low resource language, return highly coherent and sophisticated responses. it's possible that RLHF does not do a great job here but the base models are clearly cross-applying intelligence from high resource languages to low res…”

Consortium launched to build the largest open LLM原评论 ↗
被提交为 story · 1 次