Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges

TL;DR

This survey comprehensively reviews threats to federated learning throughout its life cycle, analyzes defense strategies, and discusses challenges and future directions to enhance trustworthiness and privacy in FL systems.

Contribution

It provides a detailed classification of threats and defenses in federated learning, compares various strategies, and highlights research gaps and future challenges.

Findings

Identified key threats impacting utility and privacy in FL.

Analyzed and compared different defense frameworks and their trade-offs.

Outlined future research directions and existing bottlenecks.

Abstract

Federated Learning (FL) offers innovative solutions for privacy-preserving collaborative machine learning (ML). Despite its promising potential, FL is vulnerable to various attacks due to its distributed nature, affecting the entire life cycle of FL services. These threats can harm the model's utility or compromise participants' privacy, either directly or indirectly. In response, numerous defense frameworks have been proposed, demonstrating effectiveness in specific settings and scenarios. To provide a clear understanding of the current research landscape, this paper reviews the most representative and state-of-the-art threats and defense frameworks throughout the FL service life cycle. We start by identifying FL threats that harm utility and privacy, including those with potential or direct impacts. Then, we dive into the defense frameworks, analyze the relationship between threats and defenses, and compare the trade-offs among different defense strategies. Finally, we summarize current research bottlenecks and offer insights into future research directions to conclude this survey. We hope this survey sheds light on trustworthy FL research and contributes to the FL community.