Assessing the Impact of Machine Learning-Based DDoS Attack Detection on SDN Network Performance

In recent years, the field of network security has seen significant progress. Researchers and developers have focused their efforts on designing innovative techniques to detect and counter various security threats and malicious activities. These advancements have strengthened the resilience of networks against potential attacks and have provided organizations with more effective tools to safeguard their digital assets. Within these groundbreaking developments, the application of AI technologies, notably machine learning (ML) and deep learning (DL), has proven to be remarkably successful in safeguarding software-defined networks (SDN) and bolstering the comprehensive internet security framework to defend against distributed denial-ofservice (DDoS) attacks. This research paper focuses on evaluating the performance of an SDN-based DDoS detection system, with a specific emphasis on measuring the time required to identify an ongoing attack. By conducting a thorough analysis of the system’s efficiency and responsiveness, this study aims to highlight the advantages of leveraging SDN and data plane programming in overcoming the shortcomings of traditional DDoS mitigation techniques. This study’s results are expected to support current initiatives aimed at strengthening cybersecurity measures and safeguarding essential systems against emerging digital threats. The research outcomes will provide valuable insights to help organizations and policymakers adapt their defense strategies in response to the constantly changing nature of cyber risks.