arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.04784cs.CRcs.LG
收藏

联邦大语言模型中的隐私泄露分析

Analysis of Privacy Leakage in Federated Large Language Models

University of Florida(佛罗里达大学)

Minh N. Vu, Truc Nguyen, Tre' R. Jeter, My T. Thai

AI总结:

本研究针对适配大语言模型的联邦学习协议缺乏全面隐私分析的问题,设计两种有理论成功率保障的主动成员推理攻击,揭示主流大语言模型的隐私漏洞,并评估差分隐私机制下的隐私泄露情况。

摘要:

随着联邦学习(Federated Learning,FL)作为大语言模型(Large Language Models,LLMs)应用的训练与调优协议被快速采用,近期研究强调需要对联邦学习进行重大调整以适配大语言模型的大规模特性。尽管作为应对措施已引入对该协议的大量调整,但目前仍缺乏针对适配后联邦学习协议的全面隐私分析。为填补这一空白,本工作从理论和实践两个维度,对用于训练大语言模型的联邦学习的隐私分析展开了深入研究。具体而言,我们设计了两种具备理论成功率保障的主动成员推理攻击,以评估各类适配后联邦学习配置的隐私泄露情况。我们将理论发现转化为实际攻击,揭示了BERT、RoBERTa、DistilBERT以及OpenAI的GPTs等主流大语言模型在多个真实世界语言数据集上存在显著隐私漏洞。此外,我们开展了全面实验,评估当数据受最先进的差分隐私(differential privacy,DP)机制保护时这些模型的隐私泄露情况。

英文摘要:

With the rapid adoption of Federated Learning (FL) as the training and tuning protocol for applications utilizing Large Language Models (LLMs), recent research highlights the need for significant modifications to FL to accommodate the large-scale of LLMs. While substantial adjustments to the protocol have been introduced as a response, comprehensive privacy analysis for the adapted FL protocol is currently lacking. To address this gap, our work delves into an extensive examination of the privacy analysis of FL when used for training LLMs, both from theoretical and practical perspectives. In particular, we design two active membership inference attacks with guaranteed theoretical success rates to assess the privacy leakages of various adapted FL configurations. Our theoretical findings are translated into practical attacks, revealing substantial privacy vulnerabilities in popular LLMs, including BERT, RoBERTa, DistilBERT, and OpenAI's GPTs, across multiple real-world language datasets. Additionally, we conduct thorough experiments to evaluate the privacy leakage of these models when data is protected by state-of-the-art differential privacy (DP) mechanisms.

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。

↑