DDOS ATTACK DETECTION USING AI BASED TECHNIQUES

Abstract

Software Defined Networking (SDN) has emerged as a revolutionary approach to network management and configuration, yet it also presents new vulnerabilities and avenues for Distributed Denial of Service (DDoS) attacks. Effective detection and mitigation of such attacks are crucial for maintaining network integrity and reliability. In this project we use the facilities available in machine learning to classify DDos attacks in SDN based networks. Utilizing a comprehensive dataset, generated with the Mininet emulator and containing over 100,000 instances of both benign and malicious traffic, we trained several machine learning models to classify network traffic. This dataset, uniquely tailored to SDN networks, contains 23 extracted and calculated features providing a detailed view of network events. This research provides valuable insights into the application of machine learning techniques in the detection and classification of DDoS attacks in SDN networks. The findings contribute to ongoing efforts to enhance network security, presenting efficient and robust machine learning models that can be used to safeguard SDN environments from DDoS attacks.