Exploiting machine learning and deep learning models for misbehavior detection in VANET

Abstract

There is an unprecedented proliferation of vehicular traffic data as the number of interconnected vehicles has increased in Vehicular Ad Hoc Networks (VANET) scenario to realize the goals of Intelligent Transportation Systems (ITS). As a result, the quantity and variety of attacks using transmitted data have risen. However, these broadcasted messages can be used to launch many security attacks as these messages are not encrypted. With the increase in the number of vehicles, the risk of misbehavior also increases as more malicious vehicles broadcast inaccurate and faulty messages. Various trust-based and deterministic misbehavior detection techniques have been proposed to identify such misbehavior. Existing solutions only address specific types of network intrusions. However, because VANET situations may involve a wide spectrum of attacks, a more robust misbehavior detection mechanism is required. This article compares the performance of several machine learning and deep learning architectures using key evaluation metrics. Furthermore, we have demonstrated a comparison of performance metrics with existing learning model-based techniques in different network scenarios.