Abstract

The rapid evolution of Internet of Vehicles (IoV) systems has enabled smart transportation through Vehicle-to-Everything (V2X) communications. Cyber dangers include message manipulation, impersonation, and denial of service (DoS) attacks put both cars and data at risk. More and more cars are connecting to the internet, which makes these attacks happen more often. Traditional Intrusion Detection Systems (IDS) often lack the capability to process high-dimensional IoV traffic data efficiently and fail to generalize across evolving attack patterns. Lightweight machine learning methods underperform in feature representation and temporal correlation detection, especially in real-time vehicular environments. This study proposes a cyberattack detection model utilizing Residual Neural Networks (ResNet) to capture complex spatiotemporal patterns in IoV data. The ResNet architecture is trained on a benchmark vehicular network dataset to classify normal and malicious traffic efficiently. ResNet’s skip connections enable deeper networks to avoid vanishing gradients and improve learning efficiency, even with limited labeled data. The proposed ResNet-based IDS achieved superior detection accuracy compared to conventional models like CNN, LSTM, and SVM. It yielded a classification accuracy of 98.7%, precision of 98.9%, and a recall of 98.3%, outperforming benchmark systems by an average margin of 5–8% in all metrics. The framework shows potential for real-time deployment in smart vehicular ecosystems.

Authors

A.P. Janani, J. Thimmiaraja
Dr Mahalingam College of Engineering and Technology, India

Keywords

Internet of Vehicles, Residual Neural Network, Cyberattack Detection, Deep Learning, Intelligent Transportation Systems