Advanced DDos Attack Detection in SD-IoT Using DNFN and Nature-Inspired Optimizations

Abstract

The purpose of this research is to improve the detection of Distributed Denial of Service (DDoS) attacks in systems that employ Software-Defined Internet of Things (SD-IoT). First, feature selection techniques such as PCA is used to improve the Deep Neuro Fuzzy Network (DNFN) model's detection accuracy of DDoS assaults. With an overall accuracy of 0.969, the findings show that the DNFN model has above average accuracy rates when applied to feature selection technique. To further improve the DDoS detection capabilities, optimization approaches like Elephant Herding Optimization (EHO) and the hybrid Elephant-Herding-Water-Cycle-Algorithm (EHWCA) are then developed. The EHWCA approach is superior than the current EHO method, as shown by a comparative study that compares the two. The DNFN model achieves an accuracy of 0.99 when optimized using EHWCA, whereas it only achieves 0.97 with EHO. The suggested system's scalability and efficiency are greatly enhanced by the inclusion of the water cycle in the optimization process. Overall, this research contributes to the development of strong cybersecurity solutions for IoT networks by demonstrating the efficacy of sophisticated optimization approaches, in particular EHWCA, in improving the detection of DDoS assaults in SD-IoT settings.