Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectives
Linlin Wang, Tianqing Zhu, Wanlei Zhou, Philip S. Yu
TL;DR
This survey analyzes the intertwined roles of privacy, security, and fairness in federated learning, arguing that gradient sharing is a central source of privacy and security risk while fairness can serve as a bridge to align these objectives. It provides a comprehensive taxonomy of privacy attacks (trained models, gradients, data) and security threats (poisoning, backdoors), and reviews defense mechanisms including differential privacy, secure aggregation, homomorphic encryption, secure MPC, and anomaly detection, alongside fairness-enhancing and personalization strategies. The authors highlight fundamental trade-offs—privacy versus fairness, security versus fairness, and privacy versus security—and discuss how fairness-oriented methods can mitigate or amplify these tensions. The work concludes with open research directions, emphasizing holistic design, trust, and the need for balancing three interconnected cyber-safety dimensions in real-world FL deployments.
Abstract
Federated learning is fast becoming a popular paradigm for applications involving mobile devices, banking systems, healthcare, and IoT systems. Hence, over the past five years, researchers have undertaken extensive studies on the privacy leaks, security threats, and fairness associated with these emerging models. For the most part, these three critical concepts have been studied in isolation; however, recent research has revealed that there may be an intricate interplay between them. For instance, some researchers have discovered that pursuing fairness may compromise privacy, or that efforts to enhance security can impact fairness. These emerging insights shed light on the fundamental connections between privacy, security, and fairness within federated learning, and, by delving deeper into these interconnections, we may be able to significantly augment research and development across the field. Consequently, the aim of this survey is to offer comprehensive descriptions of the privacy, security, and fairness issues in federated learning. Moreover, we analyze the complex relationships between these three dimensions of cyber safety and pinpoint the fundamental elements that influence each of them. We contend that there exists a trade-off between privacy and fairness and between security and gradient sharing. On this basis, fairness can function as a bridge between privacy and security to build models that are either more secure or more private. Building upon our observations, we identify the trade-offs between privacy and fairness and between security and fairness within the context of federated learning. The survey then concludes with promising directions for future research in this vanguard field.