Evaluation of supervised classification approach for DDoS threat detection in Software Defined Networks

Software defined networks (SDN) are the way of the future for networking, which separate the data and control planes of network devices to enable centralized control. SDN enhances network administration and security, allowing for programmability and improved performance. However, SDN is susceptible to attacks, particularly DDoS threats, which can overwhelm the network, restrict server access, and deplete network resources. This study offers a technique based on ML for recognizing DDoS threats in SDN. Various of ML models are assessed and trained using a publicly available SDN-specific dataset. These models’ performance is examined across different attack types, with results presented using parameters including F1_score, recall, precision and accuracy. The findings indicate the efficiency of ML techniques in identifying and mitigating against DDoS assaults in SDN environments.