Enhancing DDoS Attack Detection in SDN with a Stacked Model Framework Utilizing Deep Neural Networks

Software Defined Networking enhances network management and security through centralized control, vital for the growth of consumer electronics. With the rise of smart devices and IoT systems, the demand for scalable network management has intensified. While SDN streamlines network operations and supports essential technologies, it remains vulnerable to DDoS attacks that can disrupt these services. However, SDN environments are vulnerable to Distributed Denial of Service (DDoS) attacks, posing significant risks to operational integrity. This paper analyzes the performance of various machine learning models at the individual level, providing insights into their effectiveness in detecting DDoS attacks. Based on these findings, a hybrid model is introduced, utilizing stacking techniques with a Deep Neural Network (DNN) as the meta-learner. The hybrid approach achieves a remarkable accuracy of 99.09%. The results underscore the crucial role of machine learning, particularly deep learning methodologies, in safeguarding SDN networks against cyber threats. As reliance on complex networked systems in consumer electronics increases, enhancing the security of SDN environments becomes essential for maintaining seamless operations.