A Survey on Machine Learning-Based Misbehavior Detection Systems for 5G and Beyond Vehicular Networks

Advances in Vehicle-to-Everything (V2X) technology and onboard sensors have significantly accelerated deploying Connected and Automated Vehicles (CAVs). Integrating V2X with 5G has enabled Ultra-Reliable Low Latency Communications (URLLC) to CAVs. However, while communication performance has been enhanced, security and privacy issues have increased. Attacks have become more aggressive, and attackers have become more strategic. Public Key Infrastructure (PKI) proposed by standardization bodies cannot solely defend against these attacks. Thus, in complementary of that, sophisticated systems should be designed to detect such attacks and attackers. Machine Learning (ML) has recently emerged as a key enabler to secure future roads. Various V2X Misbehavior Detection Systems (MDSs) have adopted this paradigm. However, analyzing these systems is a research gap, and developing effective ML-based MDSs is still an open issue. To this end, this paper comprehensively surveys and classifies ML-based MDSs as well as discusses and analyses them from security and ML perspectives. It also provides some learned lessons and recommendations for guiding the development, validation, and deployment of ML-based MDSs. Finally, this paper highlighted open research and standardization issues with some future directions.