Trust and Resilience in Federated Learning Through Smart Contracts Enabled Decentralized Systems

TL;DR

This paper explores a decentralized federated learning system leveraging smart contracts and IPFS to enhance trust, security, and reliability, demonstrating the feasibility of different aggregation methods through experimental validation.

Contribution

It introduces a novel federated learning architecture using blockchain smart contracts and decentralized storage to improve trust and security in collaborative model training.

Findings

Feasibility of decentralized FL with smart contracts confirmed

Comparison of averaging and proximal aggregation methods

Enhanced security and trust in federated learning systems

Abstract

In this paper, we present a study of a Federated Learning (FL) system, based on the use of decentralized architectures to ensure trust and increase reliability. The system is based on the idea that the FL collaborators upload the (ciphered) model parameters on the Inter-Planetary File System (IPFS) and interact with a dedicated smart contract to track their behavior. Thank to this smart contract, the phases of parameter updates are managed efficiently, thereby strengthening data security. We have carried out an experimental study that exploits two different methods of weight aggregation, i.e., a classic averaging scheme and a federated proximal aggregation. The results confirm the feasibility of the proposal.