Investigating Security Issues in Autonomous Vehicle

Abstract

Autonomous vehicles (AVs) are a potential technology for improving safety and driving efficiency in intelligent transportation systems (ITSs). AVs are subject to a variety of cyber-attacks, including denial-of-service, spoofing, brute force, and cross-site scripting. To solve the security issues in AV. We proposed an intrusion detection system (IDS) framework for the intelligent classification of malicious and non-malicious attacks. We utilized an ensemble-based machine learning model to efficiently classify attacks. We divided the proposed model as data collection, pre-processing data for the imbalanced tree feature selection, ensemble model, and detection. This model builds the ensemble learning using stacking the model. Finally, we evaluate an ensemble model using different ai matrix accuracy, precision, recall, and f1-score. XGBoost is out-performance in this ensemble model. This proposed model benefits to attain a high detection rate and low computational cost at the same time.