A Comprehensive Survey On Machine Learning-Based Intrusion Detection System for Vehicular Area Network Architectures

Abstract

Today, the development of communication technologies causes changes in many different areas. One of these areas is VANET (Vehicular Area Network) application area. With the increase in usage areas in the VANET field, ensuring VANET network security has become more critical. Many different systems have been developed to detect attacks on VANET networks. Machine learning-based systems are one of the most widely used methods in developing these intrusion detection systems (IDS). In this article, research on machine learning-based VANET IDS, which has been done recently in the literature, has been carried out. First, VANET architecture and security requirements are presented, then a comprehensive literature summary is given, and comparisons are made on different parameters. As a result, it has been determined that many different machine learning models are used in IDSs and perform high-performance detection. In addition to the machine learning algorithm used in the performance of IDSs, it has been shown that many different parameters play a critical role in the performance. The paper aims to guide new studies in this field with the gains that will increase the performance of intrusion detection systems because of the literature comparison (considering criteria such as machine learning model, simulation tools, dataset, machine learning algorithm, and performance criteria).