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.
@article{arxiv.2507.07637,
title = {HLF-FSL. A Decentralized Federated Split Learning Solution for IoT on Hyperledger Fabric},
author = {Carlos Beis Penedo and Rebeca P. Díaz Redondo and Ana Fernández Vilas and Manuel Fernández Veiga and Francisco Troncoso Pastoriza},
journal= {arXiv preprint arXiv:2507.07637},
year = {2025}
}