Big Data Analytics for VANET Security: A Machine Learning‐Driven Attack Monitoring System

ABSTRACT One of the most important components of the intelligent transportation systems is Vehicular Ad Hoc Networks (VANETs) that provide a possibility to communicate vehicles in real‐time to improve traffic efficiency and safety. Nevertheless, the dynamic and open aspect of VANETs leaves it vulnerable to various types of cyberattacks, including Denial‐of‐Service attacks, Sybil attacks, and blackhole attacks at the expense of network reliability and user safety. These security issues need to be overcome by engaging in proactive monitoring and smart systems of detecting threats. This paper suggests the proposal of a big data analytics framework, which will be named Machine Learning‐Driven Attack Monitoring System (ML‐AMS), to identify and categorize malicious actions within VANETs. ML‐AMS combines high‐velocity vehicle data with machine learning models, both supervised and unsupervised, to provide the opportunity to identify attacks in real‐time and react appropriately. An experimental assessment of a simulated VANET environment shows that ML‐AMS has an accuracy of 96.8%, a precision of 95.4%, and a recall of 94.7%, and is much superior to the traditional intrusion detection systems. The system is able to reduce the false alarms and at the same time with a high detection latency, which ensures a robust communication between vehicles. These findings confirm the possibility to integrate big data analytics and machine learning to improve the security of VANET. To sum up, ML‐AMS will offer a scalable and smart solution to protect vehicular networks, which will allow building safer and more dependable intelligent transportation systems.