Detection of DDoS attacks in SDN-based VANET using optimized TabNet

Vehicular Ad Hoc Network (VANET) serves as a crucial component in developing the Intelligent Transport System (ITS), which provides a range of services expected to increase road safety and improve the global driving experience. At the same time, Software Defined Network (SDN) is a promising solution for VANET communication security due to the risk related to the dynamic nature of the vehicular network. However, the centralized structure of SDN-based VANET exposes vulnerabilities to Distributed Denial of Service (DDoS) attacks, which can significantly impact the network's performance. This work presents a deep learning technique for identifying DDoS attacks in SDN-based VANET, commonly called TabNet, a cutting -edge deep learning model for tabular data that generally surpasses traditional machine learning models regarding crucial performance metrics. The model underwent hyperparameter tuning and employed Adam optimization to enhance its performance. Comparative evaluations against other machine learning algorithms demonstrated the proposed model's robustness, achieving an overall accuracy of 99.42%. Our suggested method presents a potential solution for detecting DDoS attacks in SDN-based VANET, outperforming conventional techniques in terms of accuracy and efficiency.