Abstract :

The Rapid Evolution Of Smart Vehicles And The Increasing Connectivity Of Intravehicle Networks Have Made Automotive Systems More Susceptible To Sophisticated Cyberattacks. Traditional Rule-based Security Mechanisms Are Often Inadequate In Detecting Novel Threats Within Controller Area Network (CAN) Protocols, Necessitating The Adoption Of Intelligent, Datadriven Solutions. This Paper Presents A Novel Machine Learning-based Framework For Securing Intravehicle Communications, Leveraging An Enhanced Support Vector Machine (SVM) Model Optimized Through Metaheuristic Algorithms. The Methodology Includes Systematic Feature Extraction From CAN Bus Data Streams, Enabling Precise Anomaly Detection And Real-time Threat Mitigation. Experimental Validation On Extensive Benchmark Datasets Demonstrates Superior Detection Accuracy And A Significant Reduction In False Positives Compared To Conventional Intrusion Detection Systems. The Proposed Approach Not Only Advances The State-of-the-art In Automotive Cybersecurity But Also Introduces A Scalable Architecture Suitable For Future Connected And Autonomous Vehicles. The Findings Highlight The Critical Role Of Adaptive Machine Learning Algorithms In Safeguarding Intravehicle Communications Against Emerging Cyber Threats. Keywords:Intravehicle Communication, Machine Learning, Controller Area Network (CAN), Intrusion Detection System (IDS), Automotive Cybersecurity, Anomaly Detection, Support Vector Machine (SVM), Intelligent Transportation Systems, Data-Driven Security, Connected Vehicles

Published:

19-8-2025

Issue:

Vol. 25 No. 8 (2025)

Page Nos:

246-256

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite