A Classification of Misbehavior Detection Schemes for VANETs: A Survey

Abstract

In today's era, thinking of Vehicular Ad-hoc Network (VANET) as a midrib for the leaf of academic, social, corporate, and economic activities will not be erroneous. To avoid any panic situations like road accidents, heavy tra c jams, etc., the timely availability of correct information is compulsory. The presence of malicious nodes within the network will ruin the dream of establishing a safe, secure, and accident-free vehicular network. This objective can be ful lled only when malicious nodes within the network are identi ed correctly and respective actions are taken at the right time. Therefore, there is a great requirement for e cient and intelligent misbehavior detection techniques to deal with such situations. Vehicular networks are very prone to numerous attacks, such as Sybil attacks, unauthorized access, etc. due to their dynamic nature. The main goal of this study is to discuss and bundle various available misbehavior detection schemes and respective solutions to cope with harmful attackers in the network. We have categorized different misbehavior detections on the criteria of architecture, approach, node-centric, and data-centric. The subcategorization is also given within the paper. One section of this paper focuses on the role of machine learning techniques in misbehavior detection as an emerging foot strap for further enhancement. A comparative analysis of various misbehavior detection schemes is also conducted based on performance measures like accuracy, False Positive Rate, Recall, Precision and Fmeasurement. Finally, the paper concluded by discussing open issues and various research challenges associated with misbehavior detection in the Vehicular Ad-hoc Network.

Intelligent analytics algorithms in breach detection systems for securing VANETs and data for smart transportation management

“…[18] describes the creation of an attention-based temporal Graph Convolutional Network (GCN) method that makes use of temporal features to locate anomalous graph edges within dynamic graphs. Deep auto-encoders and clustering methods were used on network's nodes in conjunction with another dynamic graph anomaly detection method that was developed in [19]. GNNbased anomaly detection strategy was proposed in [20].…”

“…Using the equation v = (v1, v2, etc., vm), where h is equal to (h1, h2, hn) visible variables V are configured as follows: Vm) and the hidden variables H = (H1, H2, Hn), with (v, h) equal to 0 and 1 in m+n, and vi and hj being binary states of first visible variable Vi as well as second hidden variable Hj, eq. (19).…”

Machine learning based novel frameworks developments and architectures for secured communication in VANETs for smart transportation

“…The primary disadvantage of cryptographic solutions is this. A robust method for detecting malicious vehicles for the Post Crash Notification application has been proposed in the study [10]. They have thought about the possibility of a false crash alert in [11] and fake vehicle position data in PCN.…”

“…(weight update). Learning rule utilized to get value for updating weights at every increment is shown in equation (10):…”

Ensemble Learning Based Malicious Node Detection in SDN-Based VANETs

“…Sangwan et al [10] reviewed and categorized various misbehavior assaults in VANETs systems based on architecture, method, node-centricity, and data-centricity. It also discussed the significance of ML methods in the context of misbehavior detection.…”