MSc Thesis Defense Announcement of Aman Kumar:"Replay Attack Detection in VANETs using Machine Learning Algorithm"

 

Date: Monday August, 22nd 2022 

Time:  9:30am-11:00am 

Meeting URL:  https://us06web.zoom.us/j/86421496356?from=addon 

Passcode: If interested in attending this event, contact the Graduate Secretary at csgradinfo@uwindsor.ca with sufficient notice before the event to obtain the passcode.

 

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 security 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 report its status to other vehicles and RSU. Replay Attack is an attack in which valid data transmission is maliciously or fraudulently repeated or delayed by an attacker, leading to traffic congestion and road accidents and can misguide other legitimate Vehicles. 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 vehicles, using machine learning (ML) algorithms. 

The proposed Machine Learning based misbehavior detection system utilizes a dataset called Vehicular Reference Misbehavior (VeReMi) Extension Dataset, which is generated using simulation tools VEINS, SUMO and OMNET++. VeReMi Extension dataset offers three different vehicle densities. This ML-based model uses BSM approach to detect Replay attack. The proposed detection framework is installed at the OBUs and RSUs, which retrieve recent BSMs of a vehicle and then quickly classifies the BSM into legitimate or attacker. 

 

Internal Reader: Dr. Mahdi Firoozjaei            

External Reader: Dr. Ning Zhang      

Advisor: Dr. Arunita Jaekel 

Chair: Dr. Sherif Saad