AI-Powered Intrusion Detection for Secure and Efficient SDN in Network Virtualization

Ensuring secure and efficient intrusion detection in Software-Defined Networking (SDN) within network virtualization is crucial for modern cybersecurity. In this context, this work presents an AI-powered hybrid deep learning model integrating CNN, LSTM, GRU, and a Transformer Encoder for feature selection. SMOTE is used to balance class distributions, therefore strengthening the model. With ROC-AUC values of 0.9628, and accuracy of 82%, therefore attesting to improved classification performance. For virtualized SDN settings, this method presents an adaptive intrusion detection, hence improving network security and dependability for useful cyber-defense purposes.