Enhancing Kubernetes Security with Feedback-Driven Machine Learning Models

Kubernetes has become the cornerstone of container orchestration in modern cloud computing, offering unmatched scalability and flexibility. However, its growing adoption has introduced critical security challenges, particularly in mitigating Denial-of-Service (DoS) attacks. This study presents an innovative seven-layer framework to enhance Kubernetes security through real-time anomaly detection and feedback-driven machine learning models. The framework integrates two core components: a Feedback Application that captures user input to improve detection precision and a Model Agent for real-time data collection, anomaly detection, and adaptive model retraining. By combining real-time metrics with user feedback, the system dynamically evolves to address emerging threats, ensuring robust protection for Kubernetes environments. Experimental results demonstrate the framework's effectiveness in achieving high anomaly detection accuracy, reducing false positives, and maintaining adaptability in dynamic, cloud-native infrastructures.