Date of Award


Publication Type



Classification algorithms, Intelligent transportation system, Machine learning algorithms, Misbehavior detection, Speed offset attacks, Vehicular ad-hoc network


A. Jaekel


S. Samet



Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.


An integral component of the Intelligent Transportation System (ITS) is the emerging technology called Vehicular ad-hoc network (VANET). VANET allows Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communication wirelessly to improve road safety, traffic congestion, and information dissemination. Communication of vehicles in a VANET network is vulnerable to various attacks. Commonly used cryptographic techniques alone are insufficient to ensure and protect vehicle message integrity and authentication from insider attacks. In such cases, additional measures are necessary to ensure the correctness of the transmitted data. Each vehicle in the network periodically broadcasts a basic safety message (BSM) that contains essential status information about a vehicle, such as its position, speed, and heading to other vehicles and Road Side Units (RSU) to report its status. A speed offset attack is where an attacker (misbehaving vehicle) misleads the network by adding an offset value to its actual speed data in each BSM. Such attacks can result in traffic congestion and road accidents; therefore, it is essential to accurately detect and identify such attackers to ensure safety in the network. This research proposes a novel data-centric approach for detecting speed offset attacks using Machine Learning (ML) and Deep Learning (DL) algorithms. Vehicular Reference Misbehavior (VeReMi) Extension Dataset is used for this research. Preliminary results indicate that the proposed model can detect malicious nodes in the network quickly and accurately.