Fantastyc: Blockchain-based Federated Learning Made Secure and Practical

TL;DR

Fantastyc introduces a blockchain-based federated learning framework that enhances security, decentralization, and scalability, addressing key challenges of integrity and confidentiality for practical deployment.

Contribution

The paper presents Fantastyc, a novel blockchain-enabled federated learning system that simultaneously tackles security, decentralization, and scalability issues.

Findings

Addresses integrity, confidentiality, and scalability challenges.

Provides a fully decentralized, traceable federated learning solution.

Enhances security and practicality of federated learning systems.

Abstract

Federated Learning is a decentralized framework that enables multiple clients to collaboratively train a machine learning model under the orchestration of a central server without sharing their local data. The centrality of this framework represents a point of failure which is addressed in literature by blockchain-based federated learning approaches. While ensuring a fully-decentralized solution with traceability, such approaches still face several challenges about integrity, confidentiality and scalability to be practically deployed. In this paper, we propose Fantastyc, a solution designed to address these challenges that have been never met together in the state of the art.