BlockFUL: Enabling Unlearning in Blockchained Federated Learning

TL;DR

BlockFUL introduces a dual-chain blockchain framework for federated learning that enables efficient unlearning of models, reducing computational costs and improving performance on standard datasets.

Contribution

The paper presents a novel dual-chain blockchain structure and new unlearning paradigms for federated learning, enhancing unlearning efficiency and traceability.

Findings

Effective reduction in data dependency and operational overhead.

Improved unlearning performance on CIFAR-10 and Fashion-MNIST datasets.

Validated with multiple neural network architectures.

Abstract

Unlearning in Federated Learning (FL) presents significant challenges, as models grow and evolve with complex inheritance relationships. This complexity is amplified when blockchain is employed to ensure the integrity and traceability of FL, where the need to edit multiple interlinked blockchain records and update all inherited models complicates the process.In this paper, we introduce Blockchained Federated Unlearning (BlockFUL), a novel framework with a dual-chain structure comprising a live chain and an archive chain for enabling unlearning capabilities within Blockchained FL. BlockFUL introduces two new unlearning paradigms, i.e., parallel and sequential paradigms, which can be effectively implemented through gradient-ascent-based and re-training-based unlearning methods. These methods enhance the unlearning process across multiple inherited models by enabling efficient consensus operations and reducing computational costs. Our extensive experiments validate that these methods effectively reduce data dependency and operational overhead, thereby boosting the overall performance of unlearning inherited models within BlockFUL on CIFAR-10 and Fashion-MNIST datasets using AlexNet, ResNet18, and MobileNetV2 models.