A Blockchain-Enabled Federated Learning System with Edge Computing for Vehicular Networks

Machine learning (ML) algorithms are essential components in autonomous driving. In most existing connected and autonomous vehicles (CAVs), a large amount of driving data collected from multiple vehicles are sent to a central server for unified training. However, data privacy and security are not well protected during the data sharing process. Moreover, the centralized architecture has some inherent issues, such as single point of failure, overload requests, intolerable delay, etc. In this article, we propose Bift: a fully decentralized machine learning system combined with federated learning and blockchain to provide a privacy-preserving ML process for CAVs. Bift enables distributed CAVs to train machine learning models locally using their own driving data and then upload the local models to the nearest mobile edge computing node (MECN) to get a better global model. More importantly, Bift provides a consensus algorithm named PoFL to resist possible adversaries. We evaluate the performance of Bift and demonstrate that Bift is scalable and robust, and can defend against malicious attacks.