Securing kubernetes: An integrated approach to ai-driven threat detection and EBPF-based security monitoring

Shaik, Nawazpasha (2025) Securing kubernetes: An integrated approach to ai-driven threat detection and EBPF-based security monitoring. World Journal of Advanced Engineering Technology and Sciences, 15 (1). pp. 1569-1576. ISSN 2582-8266

This article presents a comprehensive framework for enhancing Kubernetes security through the integration of artificial intelligence-driven threat detection and extended Berkeley Packet Filter (EBPF) monitoring technologies. As organizations increasingly adopt containerized environments for mission-critical applications, traditional security approaches have proven insufficient against sophisticated attacks targeting the dynamic nature of Kubernetes orchestration. The article proposes a novel security architecture that combines machine learning models for real-time telemetry analysis with kernel-level visibility provided by EBPF instrumentation. The article approach enables automated anomaly detection across multi-cluster deployments while dynamically enforcing security policies aligned with zero trust principles. The proposed framework addresses critical security challenges including cryptojacking, privilege escalation, and unauthorized API access with minimal performance overhead. Experimental evaluations demonstrate the effectiveness of this integrated approach compared to conventional security methods, particularly in identifying emerging threats and reducing false positives. The article contributes significant advancements to cloud-native security practices and provides a foundation for future work in adaptive policy enforcement for containerized workloads.