Blockchained Federated Learning for Secure and Privacy-Preserving Internet of Vehicles: A Comprehensive Review

Abstract

The Internet of Vehicles (IoV) connects vehicles, infrastructure, and cloud services to improve transportation efficiency through autonomous driving and intelligent traffic management. However, its strong reliance on wireless communication exposes IoV systems to significant security and privacy threats such as data tampering, GPS spoofing, and network intrusion. This paper presents a comprehensive review of how blockchain technology and federated learning (FL) can be leveraged to mitigate these vulnerabilities. The review identifies the principal security and privacy challenges in IoV, analyzes the mechanisms through which blockchain ensures integrity and trust via decentralization and cryptographic consensus, and explores how FL enables collaborative intelligence without compromising data confidentiality. Furthermore, it synthesizes recent research to derive architectural insights, highlighting the complementarity of blockchain and FL in building resilient, privacy-preserving vehicular ecosystems. Finally, the paper outlines open research challenges and provides guidelines for future work, focusing on lightweight consensus mechanisms, adaptive FL algorithms, and scalable privacy-enhancing strategies for next-generation IoV systes.