Performance Evaluation of Machine Learning-Based Misbehavior Detection Systems in VANETs: A Comprehensive Study

In recent years, the deployment of Vehicular Ad hoc Networks (VANETs) has gained significant attention due to their potential to enhance road safety and traffic efficiency. However, the dynamic nature of VANETs makes them vulnerable to various security threats, including attacks on network infrastructure and misbehavior of individual vehicles. To address these challenges, Machine Learning (ML) and Deep Learning (DL) techniques have emerged as promising solutions for the detection of attacks and misbehavior in VANETs. In this paper, we present an empirical evaluation of ML and DL approaches for misbehavior detection in the context of VANETs using realistic simulation. We employ a synthetic generated dataset that includes a wide range of attacks commonly encountered in VANETs. To simulate realistic scenarios, we utilize a popular widely used and validated network simulator (i.e., Omnet++) with different open source projects to generate VANET-specific traffic patterns and communication dynamics. An useful overview of the whole process from data generation, passing by pre-processing and model training to performance evaluation is provided with an open source guithub repository. Our evaluation encompasses different ML and DL algorithms, including support vector machines (SVM), random forests (RF), convolutional neural networks (CNN), and recurrent neural networks (RNN). We assess the performance of these approaches by measuring key metrics such as accuracy, precision, recall, and F1-score. Additionally, we compare the computational efficiency of the algorithms to identify their suitability for real-time deployment in VANET environments.