Towards Blockchain-Based Federated Machine Learning: Smart Contract for Model Inference

Abstract

Federated learning is a branch of machine learning where a shared model is created in a decentralized and privacy-preserving fashion, but existing approaches using blockchain are limited by tailored models. We consider the possibility to extend a set of supported models by introducing the oracle service and exploring the usability of blockchain-based architecture. The investigated architecture combines an oracle service with a Hyperledger Fabric chaincode. We compared two logistic regression implementations in Go language—a pure chaincode and an oracle service—at various data (2–32 k instances) and network (3–13 peers) sizes. Experiments were run to assess the performance of blockchain-based model inference using 2D synthetic and EEG eye state datasets for a supervised machine learning detection task. The benchmarking results showed that the impact on performance is acceptable with the median overhead of oracle service reaching 2–4%, depending on the dimensionality of the dataset. The overhead tends to diminish at large dataset sizes with the runtime depending on the network size linearly, where additional peers increased the runtime by 6.3 and 6.6 s for 2D and EEG datasets, respectively. Demonstrated negligible difference between implementations justifies the flexible choice of model in the blockchain-based federated learning and other machine learning applications.

Blockchain for federated learning toward secure distributed machine learning systems: a systemic survey

“…( 2018 ) Efficiency Smart Contract FL Replace Oracle service with chaincode Synthetic 2D dataset Drungilas et al. ( 2021 ) EEG Eye State dataset Dynamic Weighting FL Setting weight parameter MNIST dataset Kim and Hong ( 2019 ) Security CrowdSFL Re-encryption algorithms FEMNIST dataset Li et al. ( 2020 ) ReliableFL Improved Consensus MNIST dataset Kang et al.…”

A Blockchain and Artificial Intelligence-Based, Patient-Centric Healthcare System for Combating the COVID-19 Pandemic: Opportunities and Applications

“…The decentralized architecture for hospitals can share their data among multiple healthcare organizations without any leakage of the patients' privacy. The smart contract in the framework ensures a decentralized trust among the involved participants by defining rules for the model training agreement and automatically enforcing those obligations [72]. Smart contracts record agreements as a computer code with certain rules.…”

Can Blockchain Strengthen the Energy Internet?

“…Initiatives towards collaborative model development approaches using AI and ML techniques have given rise to Federated Learning (FL), in which individual data storage on a decentralized network is encouraged [81][82][83]. This facilitates predictive data analysis through training of a shared model using different data sets, offering capabilities of generalized model development with the benefit of privacy preservation of the user data.…”

“…Smart contracts enable the automation of iterative processes, improving the flexibility of model development and data analysis. However, challenges raised through the blockchain architecture relating scalability and smart contract security, need to be addressed further to expand the capabilities of FL techniques [83].…”