Deep Learning-Based DDoS Detection in SDN Networks with Explainable AI Transparency

Network management has been completely transformed by Software-Defined Networking (SDN), which allows for centralized control by separating the control plane from the data plane. Notwithstanding its benefits, SDN is still susceptible to Distributed Denial of Service (DDoS) attacks, which can seriously impair services by overloading network capacity. The objective of this research is to create a deep learning-based DDoS detection system specifically designed for SDN environments in order to meet the requirement for efficient detection techniques against such attacks.A variety of deep learning models, such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN), Gated Recurrent Units (GRU), and Artificial Neural Networks (ANN), were applied to the CIC-DDoS2019 dataset. ANN outperformed the other models in key measures like accuracy, precision, recall, and F1-score, with practically flawless results of 0.9999 across all metrics. The models were adjusted to increase detection accuracy and overall performance. This study improved the transparency of DDoS attack detection by assessing model performance and interpreting the model’s conclusions using Explainable AI (XAI) approaches like SHAP and LIME.