Project Abstract

The present research centres on automotive cybersecurity, with a particular focus on the Controller Area Network (CAN) bus protocol, which is an essential communication framework found in contemporary vehicles. The goal of the project is to create and deploy a reliable intrusion detection system (IDS) that can identify and stop cyberattacks on the CAN bus. Using machine learning and Python-based tools, the methodology includes data collection, pre processing, and model selection.Due to its inherent security flaws, such as its lack of authentication and encryption, the CAN bus is essential for communication between different Electronic Control Units (ECUs). As a result, it is vulnerable to a variety of cyberthreats, such as replay attacks, denial-of-service (DoS) attacks, and message spoofing. In order to protect vehicle safety and security, the IDS developed in this study uses machine learning models to examine CAN bus traffic for anomalies and suspicious activity.The report offers a thorough analysis of the IDS’s performance along with a methodology, results, and experimental setup. The study’s conclusions are discussed, along with their implications for automotive cybersecurity and recommendations for more research in this field.

Keywords: Automotive cybersecurity with a focus on the Controller Area Network (CAN) bus, Development and implementation of a robust Intrusion Detection System (IDS) for CAN bus cybersecurity, Application of machine learning to detect and mitigate cyberattacks on the Controller Area Network (CAN) bus

 Conference Details

Session: Presentation Stream 27 at Presentation Slot 1

Location: GH029 at Wednesday 8th 13:30 – 17:00

Markers: Deb Roy, Oliver Kullmann

Course: MSc Cyber Security, Masters PG

Future Plans: I’m looking for an industry placement