Vehicular ad-hoc network (VANET) is an emerging technology for vehicle-to-vehicle communication vital for reducing road accidents and traffic congestion in an Intelligent Transportation System (ITS). VANET communication is vulnerable to various attacks and cryptographic techniques are used for message integrity and authentication of vehicles in order to ensure security and privacy for vehicular communications. However, if there is an inside attacker additional measures are necessary to ensure the correctness of the transmitted data. A basic safety message (BSM) is broadcasted by each vehicle in the network periodically to transmit its status. Position falsification is an attack where the attacker broadcasts a false BSM position, leading to congestion or even accidents. It becomes imperative to detect and identify the attacker to ensure safety in the network. Although many trust-based models are researched in the past, this research proposes a feasible and efficient data-centric approach to detect malicious behavior, using machine learning (ML) algorithms.The proposed Machine Learning based misbehavior detection system utilizes labelled dataset called Vehicular Reference Misbehavior Dataset (VeReMi). VeReMi dataset offers five different types of position falsification attacks with different vehicle and attacker densities. This ML-based model uses two consecutive BSM approach to detect these attacks. Model classification on the Road-side Unit detects and could revoke malicious nodes from the network, reducing computational overhead on vehicles.
Position Falsification Detection in VANET with Consecutive BSM Approach using Machine Learning Algorithm
2021-06-18
Electronic Theses and Dissertations
Hochschulschrift
Elektronische Ressource
Englisch
DDC: | 629 |
Optimizing Environment-aware VANET Clustering using Machine Learning
Springer Verlag | 2023
|Providing VANET position integrity through filtering
IEEE | 2009
|