A Hybrid SVM-RF Machine Learning Framework for Dual-Plane DDoS Detection and Mitigation in Software-Defined Networks

The rise of Software-Defined Networks (SDNs) has revolutionized the way network management and control are handled, offering flexibility and scalability. However, this innovation also presents new challenges, especially in the form of Distributed Denial of Service (DDoS) attacks, which can severely impact network performance. This project introduces a hybrid machine learning framework for the detection and mitigation of DDoS attacks in SDNs, utilizing a combination of Support Vector Machine (SVM) and Random Forest (RF) models. The framework also incorporates hybrid models, namely Hybrid LR-KNN and Hybrid GB-XGB, to enhance detection accuracy. The target variable classes, anomaly and normal, are predicted by analyzing network traffic patterns and identifying potential DDoS activities. By integrating multiple machine learning algorithms, the proposed system aims to provide a robust solution for real-time attack detection and prevention. The framework leverages the strengths of each model, combining the precision of SVM and RF with the adaptability of hybrid models, ensuring effective mitigation of both known and unknown threats. The system was implemented and evaluated using Python, with machine learning libraries such as scikit-learn for SVM and RF, and XGBoost for hybrid models. The proposed solution offers a scalable, efficient, and real-time approach to securing SDNs from DDoS attacks, ensuring network integrity and reducing the impact of cyber threats.

Keywords: Software-Defined Networks (SDNs), Distributed Denial of Service (DDoS), Machine Learning, Support Vector Machine (SVM), Random Forest (RF), Hybrid Models, Anomaly Detection, Cybersecurity, Real-Time Detection, Python, Network Security.