Blockchain-Enabled Defense Mechanism for Protecting Federated Learning Systems Against Malicious Node Updates

Abstract

This paper aims to investigate the convergence of Federated Learning (FL) and Blockchain technology to enhance the security and robustness of machine learning systems. As the utilization of mobile devices grows, managing the complexities of unbalanced and non-independent data becomes imperative. Fed-erated Learning introduces a decentralized training approach, while Blockchain provides transparency and immutability. This study proposes a resilient solution for safeguarding FL against single points of failure (SPoF) and poisoning attacks, integrating a decentralized validation mechanism and a Proof-of-Stake consen-sus protocol. Extensive experimentation is conducted to assess the effectiveness of the proposed framework across varying degrees of adversarial device engagement. The results demonstrate the solution's efficacy in fortifying FL systems against malicious participants, with an impact observed up to 50% adversarial involvement. This underscores the potential of the approach to elevate security in the realm of decentralized machine learning.