[论文解读] Privacy Preservation in Federated Learning: Insights from the GDPR Perspective.

Nguyen B. Truong, Kai Sun+3 more|arXiv (Cornell University)|Nov 10, 2020

Privacy-Preserving Technologies in Data被引用 11

一句话总结

本文综述了联邦学习（Federated Learning, FL）中的隐私保护技术，以确保符合《通用数据保护条例》（GDPR）的要求，强调尽管数据存储在本地设备上，但模型参数仍可能泄露敏感信息。本文提出将先进的密码学与差分隐私方法集成到FL系统中，以减轻数据隐私风险，同时保持与GDPR要求的合规性。

ABSTRACT

Along with the blooming of AI and Machine Learning-based applications and services, data privacy and security have become a critical challenge. Conventionally, data is collected and aggregated in a data centre on which machine learning models are trained. This centralised approach has induced severe privacy risks to personal data leakage, misuse, and abuse. Furthermore, in the era of the Internet of Things and big data in which data is essentially distributed, transferring a vast amount of data to a data centre for processing seems to be a cumbersome solution. This is not only because of the difficulties in transferring and sharing data across data sources but also the challenges on complying with rigorous data protection regulations and complicated administrative procedures such as the EU General Data Protection Regulation (GDPR). In this respect, Federated learning (FL) emerges as a prospective solution that facilitates distributed collaborative learning without disclosing original training data whilst naturally complying with the GDPR. Recent research has demonstrated that retaining data and computation on-device in FL is not sufficient enough for privacy-guarantee. This is because ML model parameters exchanged between parties in an FL system still conceal sensitive information, which can be exploited in some privacy attacks. Therefore, FL systems shall be empowered by efficient privacy-preserving techniques to comply with the GDPR. This article is dedicated to surveying on the state-of-the-art privacy-preserving techniques which can be employed in FL in a systematic fashion, as well as how these techniques mitigate data security and privacy risks. Furthermore, we provide insights into the challenges along with prospective approaches following the GDPR regulatory guidelines that an FL system shall implement to comply with the GDPR.

研究动机与目标

• 应对人工智能和机器学习中日益严峻的数据隐私挑战，特别是在GDPR等严格法规的约束下。
• 识别尽管数据保留在本地设备上，联邦学习中仍存在的隐私风险，特别是由模型参数泄露引起的风险。
• 综述并评估适用于集成到FL系统中的最先进隐私保护技术。
• 通过技术与监管要求的对齐，提供实现GDPR合规FL系统的可操作见解。
• 突出在GDPR指导方针下构建隐私韧性FL框架所面临的挑战与未来研究方向。

提出的方法

• 系统分析适用于联邦学习的现有隐私保护技术，包括差分隐私、同态加密和安全聚合。
• 评估这些技术如何在联邦学习的跨参与方通信过程中保护模型参数，防止推理攻击。
• 评估在应用密码保护时，模型效用、通信效率与隐私保障之间的权衡。
• 将技术解决方案映射到GDPR原则，如数据最小化、目的限制以及完整性和保密性。
• 提出一个将隐私增强技术集成到FL流程中的框架，以满足GDPR合规要求。
• 考察在现实联邦学习部署中结合多种隐私技术（如差分隐私与安全聚合）的可行性与局限性。

实验结果

研究问题

• RQ1 尽管数据存储在本地设备上，联邦学习中的模型参数为何仍构成隐私风险？
• RQ2 在GDPR约束下，哪些隐私保护技术最有效地减轻FL中敏感信息的泄露？
• RQ3 在FL系统中实施差分隐私与同态加密时，面临的技术与监管权衡是什么？
• RQ4 如何设计FL系统以与数据最小化和目的限制等核心GDPR原则保持一致？
• RQ5 在保持模型性能的同时，实现端到端隐私合规的开放挑战有哪些？

主要发现

• 在联邦学习中交换的模型参数仍可能泄露敏感信息，因此即使未传输原始数据，FL在本质上仍易受隐私攻击。
• 差分隐私与安全聚合在降低联邦学习系统中成员推理攻击与模型反演攻击风险方面具有显著效果。
• 同态加密支持在加密的模型更新上进行计算，增强了保密性，但引入了显著的计算开销。
• 结合多种隐私保护技术可提升防护水平，但通常会增加通信与计算成本。
• FL中的GDPR合规不仅需要技术保障，还需明确的数据处理协议与问责机制。
• 当前解决方案在平衡隐私、效率与模型准确性方面仍面临挑战，尤其是在大规模、异构的联邦学习部署中。