HLF-FSL. A Decentralized Federated Split Learning Solution for IoT on Hyperledger Fabric

TL;DR

This paper introduces a decentralized federated split learning framework using Hyperledger Fabric, enhancing privacy and scalability for IoT applications without relying on a central server.

Contribution

It presents a novel blockchain-based architecture that combines federated and split learning, enabling decentralized, privacy-preserving model training for enterprise IoT deployments.

Findings

Achieves centralized FSL accuracy on CIFAR-10 and MNIST

Reduces per epoch training time compared to Ethereum-based solutions

Maintains minimal blockchain overhead with scalable performance

Abstract

Collaborative machine learning in sensitive domains demands scalable, privacy preserving solutions for enterprise deployment. Conventional Federated Learning (FL) relies on a central server, introducing single points of failure and privacy risks, while Split Learning (SL) partitions models for privacy but scales poorly due to sequential training. We present a decentralized architecture that combines Federated Split Learning (FSL) with the permissioned blockchain Hyperledger Fabric (HLF). Our chaincode orchestrates FSL's split model execution and peer-to-peer aggregation without any central coordinator, leveraging HLF's transient fields and Private Data Collections (PDCs) to keep raw data and model activations private. On CIFAR-10 and MNIST benchmarks, HLF-FSL matches centralized FSL accuracy while reducing per epoch training time compared to Ethereum-based works. Performance and scalability tests show minimal blockchain overhead and preserved accuracy, demonstrating enterprise grade viability.