Machine Learning Based DDoS Attack Detection in Software Defined Networks (SDN)

DDoS attacks remain a serious threat to the performance and availability of computer networks. This study provides a machine learning-based method for identifying DDoS attacks in SDN (software-defined networks). The proposed method employs support vector machine (SVM) and decision tree (DT) classifiers to monitor and analyze network traffic in real-time, spotting prospective attacks and thwarting them before they can do any harm. The testing findings show the efficiency of the proposed methodology, detecting and mitigating DDoS attacks with high accuracy while minimizing false positives. The proposed method offers a scalable and effective method for boosting the security of SDN-based networks against DDoS attacks by utilizing the centralized control plane of SDN.