High-speed threat detection in 5G SDN with particle swarm optimizer integrated GRU-driven generative adversarial...

Detecting attacks in 5G software-defined network (SDN) environments requires a comprehensive approach that leverages traditional security measures, such as firewalls, intrusion prevention systems, and specialized techniques personalized to the unique characteristics of a 5G network. The attack detection in 5G SDN involves Machine learning (ML) and Deep learning (DL) algorithms to analyze large volumes of network data and identify patterns indicative of attacks. The study's main objective is to develop an efficient DL model to improve the detection performance and respond to security breaches effectively in a 5G SDN environment. The DL model integrates the Particle Swarm Optimizer-Gated Recurrent Unit Layer-Generative Adversarial Network-Intrusion Detection System classifier (PSO-GRUGAN-IDS). The PSO optimizes the network weight of the GAN model to improve the backpropagation while generating the synthetic data (attack data) in the generator model using GRU. The discriminator model uses the PSO-optimized generator model to produce synthetic and real attack data to forecast the attack. Finally, a deep classification (IDS) model is trained using a GRU network with a GAN model-produced attack data and real data to classify whether the SDN traffic is malicious or normal. Moreover, the performance of this model is evaluated using the InSDN dataset and compared with existing DL model-based intrusion detection approaches and the results demonstrate a significantly higher accuracy rate of 98.4%, precision rate of 98%, recall rate of 98.5%, less detection time of 2.464 s, lesser Log loss rate of 1.0 and more metrics instilling confidence in the effectiveness of the proposed method.