Accelerating IoV Intrusion Detection: Benchmarking GPU-Accelerated vs CPU-Based ML Libraries

TL;DR

The paper addresses the need for real-time IoV intrusion detection by benchmarking GPU-accelerated cuML against CPU-based scikit-learn across three IoV datasets (OTIDS, GIDS, CICIoV2024) and four ML models (LR, KNN, RF, XGBoost). It demonstrates substantial speedups—up to 159x in training and 95x in prediction—while largely preserving accuracy and F1 scores, highlighting the practical potential of GPU acceleration for rapid threat detection in vehicular networks. The work also discusses trade-offs, such as cuML's fewer hyperparameters and some limitations with imbalanced data, and recommends a hybrid CPU-GPU workflow to balance speed and flexibility. These findings advance the deployment prospects of fast, scalable IoV IDS and outline concrete directions for future benchmarking, federated learning, and field testing.

Abstract

The Internet of Vehicles (IoV) may face challenging cybersecurity attacks that may require sophisticated intrusion detection systems, necessitating a rapid development and response system. This research investigates the performance advantages of GPU-accelerated libraries (cuML) compared to traditional CPU-based implementations (scikit-learn), focusing on the speed and efficiency required for machine learning models used in IoV threat detection environments. The comprehensive evaluations conducted employ four machine learning approaches (Random Forest, KNN, Logistic Regression, XGBoost) across three distinct IoV security datasets (OTIDS, GIDS, CICIoV2024). Our findings demonstrate that GPU-accelerated implementations dramatically improved computational efficiency, with training times reduced by a factor of up to 159 and prediction speeds accelerated by up to 95 times compared to traditional CPU processing, all while preserving detection accuracy. This remarkable performance breakthrough empowers researchers and security specialists to harness GPU acceleration for creating faster, more effective threat detection systems that meet the urgent real-time security demands of today's connected vehicle networks.