AI-Driven intrusion detection and prevention systems to safeguard 6G networks from cyber threats

Abstract

Abstract Sixth-generation (6G) wireless networks, which boast previously unheard-of capacity, reliability, and efficiency, are projected to begin testing and implementation as early as 2030. To meet the demands of new applications, the emphasis is currently on developing 6G networks. The advent of 6G presents additional difficulties, especially in intrusion detection, where sophisticated attacks call for cutting-edge security measures. This research proposes a novel technique using a machine learning algorithm in a 6G network cyber-attack monitoring and intrusion detection system. Here, the 6G network has been monitored, and intrusion detection for cyberattack using blockchain federated Gaussian multi-agent Q-encoder neural networks (BFGMAQENN). Then, the 6G network has been optimized using whale swarm binary wolf optimization (WSBWO). The experimental analysis has been carried out for various cyberattack datasets regarding detection accuracy, data integrity, scalability, communication overhead, and network efficiency. The proposed model attained detection accuracy of 97%, data integrity of 94%, scalability of 93%, communication overhead of 60%, and network efficiency of 98%.