TBFL: A Trusted Blockchain-based Federated Learning System
Yufang Wu, Guorong Chen, Yuhao Liu, Chao Li, Mingqing Hu, Wei Wang · 2022
Federated learning (FL) is a promising distributed machine learning architecture that allows participants to cooperatively train a global model without sharing local data. However, both the trust of a central FL server and well-designed attacks against FL have significantly restricted the development of FL. In this work, we propose TBFL, a trusted blockchain-based federated learning system. It replaces the traditional central server with the functionalities provided by a decentralized blockchain. To prevent malicious participants from attacking the global model, TBFL employs a novel model verification and a scoring mechanism to keep detecting malicious participants. In addition, TBFL leverages a scalable incentive mechanism to enhance its reliability and fairness. We demonstrate the efficacy and attack-resilience of the proposed TBFL through experimental evaluation. The results validate the great performance and security properties of TBFL in training global models.