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