Transparent Contribution Evaluation for Secure Federated Learning on Blockchain

TL;DR

This paper introduces a blockchain-based federated learning framework that ensures transparent contribution evaluation and privacy protection, addressing trust issues in collaborative machine learning.

Contribution

It proposes a novel blockchain-enabled protocol for transparent contribution assessment in federated learning, overcoming the limitations of semi-trusted servers.

Findings

Effective contribution evaluation demonstrated on handwritten digits dataset

Framework maintains participant privacy during model training

Transparent protocol enhances trust in federated learning systems

Abstract

Federated Learning is a promising machine learning paradigm when multiple parties collaborate to build a high-quality machine learning model. Nonetheless, these parties are only willing to participate when given enough incentives, such as a fair reward based on their contributions. Many studies explored Shapley value based methods to evaluate each party's contribution to the learned model. However, they commonly assume a semi-trusted server to train the model and evaluate the data owners' model contributions, which lacks transparency and may hinder the success of federated learning in practice. In this work, we propose a blockchain-based federated learning framework and a protocol to transparently evaluate each participant's contribution. Our framework protects all parties' privacy in the model building phase and transparently evaluates contributions based on the model updates. The experiment with the handwritten digits dataset demonstrates that the proposed method can effectively evaluate the contributions.