The rapid evolution of Internet of Vehicles (IoVs) technologies has ushered in an era of connected transportation, which has enabled us to collect and analyze data at an unprecedented scale. However, the vast amount of data generated by IoVs poses significant privacy and security challenges, as they may be susceptible to leakage and manipulation by malicious attackers. In this work, we explore the integration of emerging blockchain technology with federated learning to create a secure and decentralized framework for IoV data management and analysis. The proposed system leverages the immutable and transparent nature of blockchain to ensure data integrity and trust among IoV nodes, while federated learning facilitates collaborative machine learning without compromising individual data privacy. Through a combination of cryptographic techniques and consensus mechanisms, the blockchain-enabled federated learning system aims to thwart adversarial attacks, ensure secure data aggregation, and enhance the overall resilience of IoV networks. This study presents a comprehensive architecture, evaluates its performance through simulations, and demonstrates its potential in mitigating security risks in IoV environments. The findings highlight the feasibility and effectiveness of this approach, paving the way for more robust and secure IoV systems.
BlockFL: A Blockchain-enabled Federated Learning System for Securing IoVs
2024-10-07
467294 byte
Conference paper
Electronic Resource
English