Lightweight DDoS Attack Detection and Mitigation in Software-Defined Networks Using Deep Learning
Visramsetty Sujatha, S. Prabakeran · 2023
Security is becoming more critical in the age of Software Defined Networking (SDN). Distributed denial of service (DDoS) attacks, which suck up all available network and server bandwidth as well as controller and switch storage, may be launched by hackers taking advantage of security holes in SDN. This article details the planning and execution of security for SDN networks for identifying and counteracting cyber-attacks. The SDN security system has an anomaly detection and prevention module. The Convolution Neural Network model for Multilayer Perceptions (CNN-MLP) employs low-cost hybrid deep learning algorithms for traffic anomaly identification. Using the mitigation approach, the IP address of the attacker may be determined, and the controller’s flow rule commands can be used to stop any malicious traffic. Next, we analyze the SDN’s safeguards. The results of the tests show that the SDN security system can identify and stop DDoS traffic in real-time.