Decentralized Federated Learning: A Survey on Security and Privacy

Abstract

Federated learning has been rapidly evolving and gaining popularity in recent years due to its privacy-preserving features, among other advantages. Nevertheless, the exchange of model updates and gradients in this architecture provides new attack surfaces for malicious users of the network which may jeopardize the model performance and user and data privacy. For this reason, one of the main motivations for decentralized federated learning is to eliminate server-related threats by removing the server from the network and compensating for it through technologies such as blockchain. However, this advantage comes at the cost of challenging the system with new privacy threats. Thus, performing a thorough security analysis in this new paradigm is necessary. This survey studies possible variations of threats and adversaries in decentralized federated learning and overviews the potential defense mechanisms. Trustability and verifiability of decentralized federated learning are also considered in this study.

arXiv commentAccepted for publication in IEEE Transactions on Big Data

References in corpus (14)

• Deep Learning with Differential Privacy
• Federated Learning: Challenges, Methods, and Future Directions
• Hyperledger Fabric: A Distributed Operating System for Permissioned Blockchains
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• A Survey on Consensus Mechanisms and Mining Strategy Management in Blockchain Networks
• A Blockchain-based Decentralized Federated Learning Framework with Committee Consensus
• Secure Federated Transfer Learning
• Blockchain for 5G and Beyond Networks: A State of the Art Survey
• HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning
• Privacy Preserving Vertical Federated Learning for Tree-based Models
• FLAD: Adaptive Federated Learning for DDoS Attack Detection
• Privacy Amplification by Iteration
• A Stream Learning Approach for Real-Time Identification of False Data Injection Attacks in Cyber-Physical Power Systems
• Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms

Cited by in corpus (7)

• Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges
• Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Survey
• Federated Continual Learning: Concepts, Challenges, and Solutions
• Defending Against Diverse Attacks in Federated Learning Through Consensus-Based Bi-Level Optimization
• Noise-Robust and Resource-Efficient ADMM-based Federated Learning
• De-DSI: Decentralised Differentiable Search Index
• CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection