Privacy-Preserving in Blockchain-based Federated Learning Systems

TL;DR

The paper addresses privacy challenges in Blockchain-enabled Federated Learning (BCFL) by providing a systematic survey (2018–2023) of privacy attacks and defenses. It introduces a taxonomy of BCFL privacy solutions, including Differential Privacy, Homomorphic Encryption, Secure Multiparty Computation, reward-based incentives, and cross-chain Federated Learning, and discusses their applicability across Healthcare, Industry 5.0, and IoV. It also covers cross-chain BCFL as a scalability solution and identifies open issues such as computational overhead, gas costs, and collusion risks, offering future directions like zero-knowledge proofs and optimized consensus. Overall, the work serves as a comprehensive reference for researchers and practitioners to understand the current BCFL privacy landscape and to guide future developments and deployments.

Abstract

Federated Learning (FL) has recently arisen as a revolutionary approach to collaborative training Machine Learning models. According to this novel framework, multiple participants train a global model collaboratively, coordinating with a central aggregator without sharing their local data. As FL gains popularity in diverse domains, security, and privacy concerns arise due to the distributed nature of this solution. Therefore, integrating this strategy with Blockchain technology has been consolidated as a preferred choice to ensure the privacy and security of participants. This paper explores the research efforts carried out by the scientific community to define privacy solutions in scenarios adopting Blockchain-Enabled FL. It comprehensively summarizes the background related to FL and Blockchain, evaluates existing architectures for their integration, and the primary attacks and possible countermeasures to guarantee privacy in this setting. Finally, it reviews the main application scenarios where Blockchain-Enabled FL approaches have been proficiently applied. This survey can help academia and industry practitioners understand which theories and techniques exist to improve the performance of FL through Blockchain to preserve privacy and which are the main challenges and future directions in this novel and still under-explored context. We believe this work provides a novel contribution respect to the previous surveys and is a valuable tool to explore the current landscape, understand perspectives, and pave the way for advancements or improvements in this amalgamation of Blockchain and Federated Learning.

Figures (11)

• Figure 1: The PRISMA flow diagram visually outlines the various phases of the systematic review process.
• Figure 2: Centralized ML Architecture
• Figure 3: Distributed On-Site ML Architecture
• Figure 4: Federated Learning Architecture
• Figure 5: A schematic diagram of the Federated Learning workflow