Date of Award

Fall 2021

Publication Type

Thesis

Degree Name

M.Sc.

Department

Computer Science

First Advisor

A. Jaekel

Second Advisor

A. Sarker

Third Advisor

K. Selvarajah

Keywords

Vehicular communication, Misbehavior detection, Deep learning, Vehicular Ad hoc Network

Rights

info:eu-repo/semantics/openAccess

Abstract

Vehicular Ad hoc Network (VANET) is an evolving subset of MANET. It's deployed on the roads, where vehicles act as mobile nodes. Active security and Intelligent Transportation System (ITS) are integral applications of VANET, which require stable and uninterrupted vehicle-to-vehicle communication technology. VANET, is a type of wireless network, due to which it is quite prone to security attacks. Extremely dynamic connections, sensitive data sharing and time-sensitivity of this network make it a vulnerable to security attacks. The messages shared between the vehicles are the basic safety message (BSM), these messages are broadcasted by each vehicle in the network to report its status to the other vehicles and Road Side Unit (RSU). One common attack is to use position falsification to hamper the roadside safety, leading to road accidents and congestion. Identifying malicious nodes involved in such attacks is crucial to ensure safety in the network. The proposed research presents a neural network based approach for detecting position falsification attacks in VANET.

The proposed Deep Learning-based detection of attackers is done using the dataset called Vehicular Reference Misbehavior Dataset (VeReMi). VeReMi dataset provides five classes of attackers, each broadcasting fabricated coordinates concerning the type. This MLP-based model uses resampled single BSM and two consecutive BSM to detect these attacks.

Share

COinS