Integrating Anomaly Detection into DevSecOps Pipelines for Continuous Cloud Security

Abstract

The integration of anomaly detection into DevSecOps pipelines represents a paradigm shift in continuous cloud security, moving beyond static vulnerabilities to identify dynamic runtime threats. As cloud-native architectures expand, the traditional security gates in Continuous Integration and Continuous Deployment (CI/CD) pipelines often fail to detect sophisticated, zero-day attacks or nuanced behavioral anomalies. This paper explores the design, deployment, and evaluation of an AI-driven anomaly detection framework embedded directly within DevSecOps workflows. By leveraging unsupervised machine learning algorithms, the proposed framework 
continuously monitors pipeline telemetry, code commits, and runtime behaviors to flag deviations from established baselines.