arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.08402cs.CR
收藏

联邦学习中的公平性与隐私保护:综述

Fairness and Privacy-Preserving in Federated Learning: A Survey

Taki Hasan Rafi, Faiza Anan Noor, Tahmid Hussain, Dong-Kyu Chae

AI总结:

本文综述联邦学习中的隐私保护与公平性问题,梳理隐私机制、公平概念及兼顾二者的有限研究,并指出未来方向。

摘要:

联邦学习(FL)作为一种分布式机器学习,随着隐私感知机器学习(ML)系统的出现而受到欢迎;这类系统通过构建全局模型,并让去中心化的边缘客户端在其私有数据上进行个性化训练,从而防止隐私泄露。然而,现有工作采用安全多方计算(SMC)、差分隐私(DP)等隐私机制,这些机制极易受到干扰,并伴随巨大的计算开销、较低的准确率等问题。随着FL系统部署日益广泛,确保公平性并维持客户端在FL系统中的积极参与具有挑战性。极少有工作能够为众多多样化客户端提供合理令人满意的性能,也未能防止FL系统中针对特定人群的潜在偏见。当前努力未能在FL系统的隐私、公平性和模型性能之间取得平衡,并且还容易受到许多其他问题的影响。本文提供了一项全面综述,阐述FL的基本概念、现有隐私挑战、技术以及与FL中隐私相关的工作。我们还广泛概述了日益增加的公平性挑战、现有公平性概念,以及少数同时尝试解决FL中隐私与公平性的工作。通过全面描述现有FL系统,我们提出了与隐私保护和公平感知FL系统挑战相关的潜在未来方向。

英文摘要:

Federated learning (FL) as distributed machine learning has gained popularity as privacy-aware Machine Learning (ML) systems have emerged as a technique that prevents privacy leakage by building a global model and by conducting individualized training of decentralized edge clients on their own private data. The existing works, however, employ privacy mechanisms such as Secure Multiparty Computing (SMC), Differential Privacy (DP), etc. Which are immensely susceptible to interference, massive computational overhead, low accuracy, etc. With the increasingly broad deployment of FL systems, it is challenging to ensure fairness and maintain active client participation in FL systems. Very few works ensure reasonably satisfactory performances for the numerous diverse clients and fail to prevent potential bias against particular demographics in FL systems. The current efforts fail to strike a compromise between privacy, fairness, and model performance in FL systems and are vulnerable to a number of additional problems. In this paper, we provide a comprehensive survey stating the basic concepts of FL, the existing privacy challenges, techniques, and relevant works concerning privacy in FL. We also provide an extensive overview of the increasing fairness challenges, existing fairness notions, and the limited works that attempt both privacy and fairness in FL. By comprehensively describing the existing FL systems, we present the potential future directions pertaining to the challenges of privacy-preserving and fairness-aware FL systems.

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。

↑