Robust IDS for SDN-iot networks with residual GRU in two-tier PRF MAC and gaussian-gbell hybrid

Abstract

Network administration has been converted by the quick spread of IoT devices and the rise of SDN, but serious security risks exist. Because they frequently have limited resources, IoT devices are exposed to attacks like man-in-the-middle, brute force, and DDoS. An IDS that is strong and designed for SDN-IoT cloud networks is essential. This paper proposed a hybrid IDS framework that uses the Gaussian-Gbell and Residual GRU models to increase detection efficiency and robustness. While Residual GRU targets the long-term dependencies and vanishing gradient problems in sequential data processing, the Gaussian-Gbell hybrid, which combines Gaussian and Generalized Bell functions, improves flexibility in capturing non-linear data patterns. Using SDN-IoT traffic circumstances the proposed model shows a 99.7 percentage of accuracy rate in real-time cyber threat detection and mitigation. The architecture highlights robustness against adversarial attacks and low processing overhead for real-time activities while balancing scalability, performance and security. The model provides better F1 scores, precision, and recall than conventional methods, making it a dependable IDS solution for changing network settings. Future research aims to increase adaptation to new threats, combine federated learning for distributed IoT security and combine minimal encryption for devices with limited resources. This study emphasizes how crucial sophisticated IDS are to protecting dynamic SDN-IoT cloud networks from the ever-increasing security landscape while maintaining scalability and operational predictability.