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.

翻译：联邦学习（FL）作为一种分布式机器学习方法，随着隐私感知机器学习（ML）系统的兴起而广受欢迎。它通过构建全局模型并在去中心化边缘客户端本地私有数据上进行个性化训练，有效防止隐私泄露。然而，现有研究采用了安全多方计算（SMC）、差分隐私（DP）等隐私机制，这些方法极易受到干扰、计算开销巨大、准确率较低。随着FL系统部署日益广泛，确保公平性并维持客户端积极参与成为挑战。现有极少工作能保证众多不同客户端获得合理满意的性能，且未能防止FL系统中对特定群体可能存在的偏见。当前努力难以在FL系统的隐私、公平性和模型性能之间取得平衡，且易受多种额外问题影响。本文提供全面综述，阐述FL基本概念、现有隐私挑战、技术及隐私相关研究工作。同时，我们对日益增长的公平性挑战、现有公平性概念以及少量同时兼顾隐私与公平性的FL工作进行了广泛概述。通过全面描述现有FL系统，我们提出了面向隐私保护与公平感知FL系统挑战的潜在未来方向。