AI Driven Techniques for Distribution Denial Of Service Anomaly Detection in Software Defined Networks

The surge in network traffic and the evolution of cyber threats have amplified the risk ofDistributed Denial of Service (DDoS) attacks in software-defined networks (SDNs).Traditional security solutions often fall short in mitigating these sophisticated attacks due totheir limited adaptability and accuracy. This project presents a novel approach that integratesmachine learning (ML) and deep learning (DL) techniques to effectively detect DDoSanomalies in SDNs. By analyzing network traffic patterns, our method combines the strengthsof both ML and DL algorithms to accurately distinguish between normal and malicious traffic.Experimental results demonstrate the robustness of this approach, achieving high accuracy andminimal false positives in DDoS detection. This study highlights the potential of ML and DL-based techniques as reliable, adaptive security measures for protecting SDN environments fromevolving DDoS threats.