A Dynamic Framework for DDOS Attack Detection and Mitigation in Software Defined Network Using Machine Learning

In response to the escalating frequency and complexity of Distributed Denial of Service attacks, safeguarding network infrastructures has become an imperative challenge. This paper introduces an innovative solution for DDoS attack detection and mitigation within the realm of Software-Defined Networking (SDN). The approach leverages a Ryu controller and integrates a Decision Tree classifier, employing machine learning to discern intricate traffic patterns indicative of DDoS attacks. Complementing this, the system deploys rate limiting and port blocking mechanisms as proactive measures to thwart malicious activities. Through rigorous experimentation, our results affirm the efficacy of the proposed system, demonstrating its ability for real-time threat identification and mitigation. This research signifies a significant step toward fortifying networks against the evolving landscape of cyber threats.