Blockchain-enabled Trustworthy Federated Unlearning

TL;DR

This paper introduces a blockchain-based framework for federated unlearning that ensures trustworthy data removal, improves efficiency, and addresses privacy concerns in distributed machine learning.

Contribution

It proposes a novel blockchain-enabled protocol with a proof of unlearning and an adaptive retraining mechanism, enhancing data removal and training efficiency.

Findings

Achieves better data removal than existing frameworks.

Reduces computational overhead in federated unlearning.

Demonstrates improved trustworthiness and efficiency.

Abstract

Federated unlearning is a promising paradigm for protecting the data ownership of distributed clients. It allows central servers to remove historical data effects within the machine learning model as well as address the "right to be forgotten" issue in federated learning. However, existing works require central servers to retain the historical model parameters from distributed clients, such that allows the central server to utilize these parameters for further training even, after the clients exit the training process. To address this issue, this paper proposes a new blockchain-enabled trustworthy federated unlearning framework. We first design a proof of federated unlearning protocol, which utilizes the Chameleon hash function to verify data removal and eliminate the data contributions stored in other clients' models. Then, an adaptive contribution-based retraining mechanism is developed to reduce the computational overhead and significantly improve the training efficiency. Extensive experiments demonstrate that the proposed framework can achieve a better data removal effect than the state-of-the-art frameworks, marking a significant stride towards trustworthy federated unlearning.