Detecting Traffic Diversion Using Metaheuristic Algorithm in SDN

With the increasing prevalence of Software-Defined Networking (SDN) and the growing demand for network resources, the threat of traffic diversion attacks in SDN environments poses a significant risk to network security and performance. Conventional methods for detecting these attacks often fall short of identifying sophisticated and dynamic diversion tactics. In response to this challenge, we present a novel approach to tackle traffic diversion attacks in SDN. Our proposed technique leverages metaheuristic algorithms, specifically a Genetic Algorithm (GA), to improve traffic diversion detection's precision and effectiveness. The primary objective is to provide network administrators with a robust and adaptive tool for identifying and mitigating diversion attacks. Through rigorous testing and evaluation, our proposed algorithm demonstrates exceptional performance. It achieved a high level of accuracy, exceeding 70 %, a precision of 94%, a recall of 92%, and a F1-score of 93%. in identifying diversion attacks while maintaining a low false positive rate. The algorithm's adaptability ensures it can respond effectively to evolving diversion tactics, making it well-suited for dynamic SDN environments. The proposed algorithm is scalable as it can be adapted to the changing of network conditions, such as traffic levels. The proposed algorithm contributes to the enhancement of SDN security, safeguarding network integrity and reliability in the face of evolving threats.