Secure and Efficient Federated Learning Through Layering and Sharding Blockchain

TL;DR

This paper introduces ChainFL, a blockchain-based federated learning system that uses layering and sharding to improve efficiency and robustness, especially for resource-constrained IoT devices.

Contribution

It proposes a novel two-layer blockchain architecture with sharding and a DAG-based mainchain, enhancing scalability and robustness of federated learning.

Findings

Up to 14% improvement in training efficiency.

Threefold increase in robustness.

Effective handling of large-scale IoT FL tasks.

Abstract

Introducing blockchain into Federated Learning (FL) to build a trusted edge computing environment for transmission and learning has attracted widespread attention as a new decentralized learning pattern. However, traditional consensus mechanisms and architectures of blockchain systems face significant challenges in handling large-scale FL tasks, especially on Internet of Things (IoT) devices, due to their substantial resource consumption, limited transaction throughput, and complex communication requirements. To address these challenges, this paper proposes ChainFL, a novel two-layer blockchain-driven FL system. It splits the IoT network into multiple shards within the subchain layer, effectively reducing the scale of information exchange, and employs a Direct Acyclic Graph (DAG)-based mainchain as the mainchain layer, enabling parallel and asynchronous cross-shard validation. Furthermore, the FL procedure is customized to integrate deeply with blockchain technology, and a modified DAG consensus mechanism is designed to mitigate distortion caused by abnormal models. To provide a proof-of-concept implementation and evaluation, multiple subchains based on Hyperledger Fabric and a self-developed DAG-based mainchain are deployed. Extensive experiments demonstrate that ChainFL significantly surpasses conventional FL systems, showing up to a 14% improvement in training efficiency and a threefold increase in robustness.