Advancing Intrusion Detection Systems on the Internet of Vehicles: Mitigating DoS and Spoofing Attacks in CAN Bus Networks

Attarde, Pushpak Kishor (2024) Advancing Intrusion Detection Systems on the Internet of Vehicles: Mitigating DoS and Spoofing Attacks in CAN Bus Networks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (622kB) | Preview
Preview	PDF (Configuration Manual) Download (600kB) | Preview

Abstract

This report studies the “Intrusion Detection System (IDS)” methodologies for actually “identifying and mitigating” Denial of Service (DoS) and spoofing attacks in the “Controller Area Network (CAN) bus” of “Internet of Vehicles (IoV)” systems. This study specifically employs secondary data, the study utilises machine learning approaches, especially “Random Forest and Logistic Regression”, as well as deep learning models to create strong detection mechanisms. The investigation is performed in Jupyter Notebook utilising Python programming language, leveraging its comprehensive libraries and instruments for data analysis and machine learning. In this research both CICIDS 2017, and CICIoV 2024 dataset are used. The focus point is determined in the case of CICIoV 2024. This research explores the results to show that both “machine learning and deep learning approaches” greatly improve the detection accuracy and reaction time to possible threats. The Random Forest algorithm demonstrated increased precision in differentiating normal and attack traffic, while the Logistic Regression delivered beneficial understandings of the attribute significance of attack routines. The deep learning standards, on the other hand, excelled in catching complex designs and irregularities in the data. This thorough process not only supports the protection of IoV systems but also delivers a scalable framework for prospective analysis in vehicular network security.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haycock, Barry UNSPECIFIED
Uncontrolled Keywords:	DoS; IoV; IDS; CAN bus; spoofing attack; Random Forest; Logistic Regression; Deep Learning; RNN; CNN; LSTM
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	07 Aug 2025 09:48
Last Modified:	07 Aug 2025 09:48
URI:	https://norma.ncirl.ie/id/eprint/8459

Actions (login required)

View Item