arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.01424cs.CLcs.AI
收藏

识别并缓解源自语言模型的隐私风险:一项综述

Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey

University College London(伦敦大学学院);The Alan Turing Institute(艾伦·图灵研究所)

Victoria Smith, Ali Shahin Shamsabadi, Carolyn Ashurst, Adrian Weller

AI总结:

该研究针对大语言模型训练数据记忆引发的隐私泄露问题,推出首个LLM数据隐私SoK,从攻击维度分类、现有攻击梳理、缓解策略调研、研究空白识别四方面系统梳理相关领域知识。

摘要:

近年来,大语言模型(Large Language Models, LLMs)性能大幅提升,这得益于模型规模的扩大和训练数据的丰富。这一进展引发了各行业和公众的广泛关注与应用。然而,机器学习模型的训练数据记忆程度随模型规模增长而提升,这对LLMs而言尤为值得关注。被记忆的文本序列可能直接从LLMs中泄露,对数据隐私构成严重威胁。目前已开发出多种攻击LLMs以提取其训练数据的技术。随着这些模型规模持续增长,这一问题变得愈发关键。为帮助研究人员和政策制定者了解隐私攻击与缓解措施的研究现状,包括仍需开展更多工作的方向,我们提出了首个针对LLMs数据隐私的SoK(系统知识梳理)。我们:(i)确定了LLMs攻击差异的显著维度分类体系;(ii)系统化梳理现有攻击方法,利用我们的维度分类体系突出关键趋势;(iii)调研现有缓解策略,阐明其优势与局限性;(iv)指出关键研究空白,明确待解决的问题和值得关注的领域。

英文摘要:

Large Language Models (LLMs) have shown greatly enhanced performance in recent years, attributed to increased size and extensive training data. This advancement has led to widespread interest and adoption across industries and the public. However, training data memorization in Machine Learning models scales with model size, particularly concerning for LLMs. Memorized text sequences have the potential to be directly leaked from LLMs, posing a serious threat to data privacy. Various techniques have been developed to attack LLMs and extract their training data. As these models continue to grow, this issue becomes increasingly critical. To help researchers and policymakers understand the state of knowledge around privacy attacks and mitigations, including where more work is needed, we present the first SoK on data privacy for LLMs. We (i) identify a taxonomy of salient dimensions where attacks differ on LLMs, (ii) systematize existing attacks, using our taxonomy of dimensions to highlight key trends, (iii) survey existing mitigation strategies, highlighting their strengths and limitations, and (iv) identify key gaps, demonstrating open problems and areas for concern.

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。

↑