Fairness, Integrity, and Privacy in a Scalable Blockchain-based Federated Learning System
This addresses the problem of limited adoption of federated learning in practice due to difficulties in ensuring fairness, integrity, and privacy for all clients, representing an incremental improvement by combining existing technologies.
The paper tackled the challenge of implementing federated learning systems that achieve fairness, integrity, and privacy by proposing a system that combines blockchain technology, local differential privacy, and zero-knowledge proofs, demonstrating through a proof-of-concept with multiple linear regression that these technologies can be integrated into a scalable and transparent system.
Federated machine learning (FL) allows to collectively train models on sensitive data as only the clients' models and not their training data need to be shared. However, despite the attention that research on FL has drawn, the concept still lacks broad adoption in practice. One of the key reasons is the great challenge to implement FL systems that simultaneously achieve fairness, integrity, and privacy preservation for all participating clients. To contribute to solving this issue, our paper suggests a FL system that incorporates blockchain technology, local differential privacy, and zero-knowledge proofs. Our implementation of a proof-of-concept with multiple linear regression illustrates that these state-of-the-art technologies can be combined to a FL system that aligns economic incentives, trust, and confidentiality requirements in a scalable and transparent system.