An improved robust misbehavior detection scheme for Vehicular Ad Hoc Network

Abstract

Vehicular Ad Hoc Networks (VANETs) have emerged to improve road safety and traffic efficiency and provide passengers comfort. Most VANET applications rely on the cooperation among vehicles sharing their sensed information. However, misbehaving vehicles which send false information can disrupt the VANETs potential. Although many solutions have been proposed to defend against misbehaving vehicles in VANET, most of these solutions relays on honest majority assumptions and are thus vulnerable to collusion attacks. Colluding vehicles send fake information, and because detection depends on cooperation, such information misleads benign vehicles to make an accurate decision. This study proposes an improved Robust Misbehavior Detection Scheme (iRMDS) by replacing the statistics-based detection threshold, which assumes an honest majority, with a machine learning-based classifier. A Neuro-Kalman-Based Robust Misbehavior detection scheme is proposed in three phases. In the first phase, attackers-Independent features are extracted from signal properties such as the receive signal strength and signal direction and have been integrated with context information features. In the second phase, the Kalman filter algorithm has been designed to extract consistent patterns of context information for each vehicle. That is, the innovation errors of the Kalman filter have been utilized as the input features to train the misbehavior detection model. In the third phase, the artificial neural network algorithm is integrated with the outputs of the Kalman Filter algorithm to recognize the malicious pattern. Results show that the overall performance of the proposed iRMDS solution achieves a 3.44% improvement compared to the related work. Such enhancement is promising in realizing reliable VANET applications to improve road safety, traffic efficiency, and passenger comfort.