A Fuzzy-Based Context-Aware Misbehavior Detecting Scheme for Detecting Rogue Nodes in Vehicular Ad Hoc Network

• Main Authors: Alghamdi, N.S (Author), Alkhammash, E.H (Author), Al-Rimy, B.A.S (Author), Ghaleb, F.A (Author), Saeed, F. (Author)
• Format: Article
• Language: English
• Published: MDPI 2022
• Subjects: ART model; context uncertainty; Context uncertainty; context-aware; Context-Aware; Detection rates; Efficiency; Fuzzy inference; fuzzy inference system; Fuzzy inference systems; Fuzzy neural networks; Fuzzy systems; misbehavior detection; Misbehavior detection; Motor transportation; State of the art; Traffic efficiency; Uncertainty; VANET; Vehicles; Vehicular ad hoc networks; Vehicular Adhoc Networks (VANETs)
• Online Access: View Fulltext in Publisher

 A vehicular ad hoc network (VANET) is an emerging technology that improves road safety, traffic efficiency, and passenger comfort. VANETs’ applications rely on co-operativeness among vehicles by periodically sharing their context information, such as position speed and acceleration, among others, at a high rate due to high vehicles mobility. However, rogue nodes, which exploit the co-operativeness feature and share false messages, can disrupt the fundamental operations of any potential application and cause the loss of people’s lives and properties. Unfortunately, most of the current solutions cannot effectively detect rogue nodes due to the continuous context change and the inconsideration of dynamic data uncertainty during the identification. Although there are few context-aware solutions proposed for VANET, most of these solutions are data-centric. A vehicle is considered malicious if it shares false or inaccurate messages. Such a rule is fuzzy and not consistently accurate due to the dynamic uncertainty of the vehicular context, which leads to a poor detection rate. To this end, this study proposed a fuzzy-based context-aware detection model to improve the overall detection performance. A fuzzy inference system is constructed to evaluate the vehicles based on their generated information. The output of the proposed fuzzy inference system is used to build a dynamic context reference based on the proposed fuzzy inference system. Vehicles are classified into either honest or rogue nodes based on the deviation of their evaluation scores calculated using the proposed fuzzy inference system from the context reference. Extensive experiments were carried out to evaluate the proposed model. Results show that the proposed model outperforms the state-of-the-art models. It achieves a 7.88% improvement in the overall performance, while a 16.46% improvement is attained for detection rate compared to the state-of-the-art model. The proposed model can be used to evict the rogue nodes, and thus improve the safety and traffic efficiency of crewed or uncrewed vehicles designed for different environments, land, naval, or air. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.