Enhancing security in software defined Networking using machine learning and networking algorithm

Abstract

In Software Defined Networking (SDN), control planes and data planes work simultaneously; which offers flexibility and programmability, and also comes with security vulnerabilities. As big networking systems are planning to adapt SDN for its advantages, the vulnerabilities should be treated seriously. In recent years, the rapid growth of SDN has led to a USD 812.13 million market in 2022, projected to reach USD 7436.01 million by 2028. However, the susceptibility of SDN to various attacks including DDoS, Brute force attacks, link failures, Heartbleed, and session hijacking poses a significant risk. These attacks can overwhelm SDN controllers or switches, disrupting network traffic and causing service outages. Therefore, this paper focuses on DDoS attacks on SDN. To detect and mitigate DDoS attacks in SDN, data analysis along with Machine Learning and algorithms were implemented. Here we proposed an network algorithm which works on DDoS attacks in SDN environment with the accuracy level of almost 100%.