Secure Decentralized Learning with Blockchain

TL;DR

This paper introduces Blockchain-based Decentralized Federated Learning (BDFL), enhancing privacy, security, and incentives in distributed machine learning by using blockchain for model verification, reputation management, and dynamic network updates.

Contribution

The paper proposes a novel blockchain-enabled framework for decentralized federated learning that addresses security, trust, and incentive issues in distributed model training.

Findings

BDFL achieves fast convergence and high accuracy even with 30% malicious clients.

The reputation mechanism effectively mitigates poisoning attacks.

Blockchain integration enhances security and trustworthiness in decentralized learning.

Abstract

Federated Learning (FL) is a well-known paradigm of distributed machine learning on mobile and IoT devices, which preserves data privacy and optimizes communication efficiency. To avoid the single point of failure problem in FL, decentralized federated learning (DFL) has been proposed to use peer-to-peer communication for model aggregation, which has been considered an attractive solution for machine learning tasks on distributed personal devices. However, this process is vulnerable to attackers who share false models and data. If there exists a group of malicious clients, they might harm the performance of the model by carrying out a poisoning attack. In addition, in DFL, clients often lack the incentives to contribute their computing powers to do model training. In this paper, we proposed Blockchain-based Decentralized Federated Learning (BDFL), which leverages a blockchain for decentralized model verification and auditing. BDFL includes an auditor committee for model verification, an incentive mechanism to encourage the participation of clients, a reputation model to evaluate the trustworthiness of clients, and a protocol suite for dynamic network updates. Evaluation results show that, with the reputation mechanism, BDFL achieves fast model convergence and high accuracy on real datasets even if there exist 30\% malicious clients in the system.