AI-Enhanced Security for Large-Scale Kubernetes Clusters: Advanced Defense and Authentication for National Cloud Infrastructure

This paper presents an AI-enhanced security framework for large-scale Kubernetes clusters, addressing the critical need for advanced defense and authentication mechanisms in national cloud infrastructures. The proposed system combines machine learning models for threats, policy creation, and intelligent resource allocation to provide security across the environment. An experiment simulating a 1,000-node Kubernetes cluster was used to evaluate the framework's performance over 30 days. The results showed a significant improvement over traditional security methods, including 99.97% threat detection accuracy, a false positive rate of 0.005%, and an 85% reduction in average response time to security threats. The framework exhibits excellent performance, maintaining consistent performance up to 10,000 nodes with only 7% degradation. Notably, the change resulted in a 27% improvement in overall stability throughout the trial. This research has a significant impact on the security of the country's airspace, providing effective protection against threats, insider attacks, and ongoing threats. The study concludes by discussing limitations and future research directions, emphasizing the need for real-world deployment and research on possible AI architectures. Better for limited spaces.