Intrusion Detection in Internet of Vehicles Using Machine Learning

TL;DR

This paper develops a machine learning-based intrusion detection system for IoV, classifying malicious CAN bus traffic to enhance vehicle cybersecurity, using the CiCIoV2024 dataset and analyzing various attack patterns.

Contribution

It introduces a novel ML approach for classifying IoV cyber-attacks on CAN traffic, leveraging the CiCIoV2024 dataset and analyzing multiple attack types.

Findings

Clear structural differences between attack types and benign data

Multi-class classification problem identified

Foundation for effective ML-based intrusion detection

Abstract

The Internet of Vehicles (IoV) has evolved modern transportation through enhanced connectivity and intelligent systems. However, this increased connectivity introduces critical vulnerabilities, making vehicles susceptible to cyber-attacks such Denial-ofService (DoS) and message spoofing. This project aims to develop a machine learning-based intrusion detection system to classify malicious Controller Area network (CAN) bus traffic using the CiCIoV2024 benchmark dataset. We analyzed various attack patterns including DoS and spoofing attacks targeting critical vehicle parameters such as Spoofing-GAS - gas pedal position, Spoofing-RPM, Spoofing-Speed, and Spoofing-Steering\_Wheel. Our initial findings confirm a multi-class classification problem with a clear structural difference between attack types and benign data, providing a strong foundation for machine learning models.