Published Paper Details:

The transition from traditional perimeter-based network security to Zero Trust Architecture (ZTA) represents a major shift in modern cybersecurity. This paper reviews the implementation of AI-driven continuous authentication mechanisms in Identity and Access Management (IAM) systems. It focuses on the use of hybrid machine learning models, combining Isolation Forest for anomaly detection and Random Forest for contextual risk evaluation. These models generate a dynamic risk score that enables adaptive access control decisions such as granting access, enforcing multi-factor authentication, or blocking sessions. The study also highlights the integration of identity risk telemetry with Security Information and Event Management (SIEM) systems using standardized schemas. The findings suggest that lightweight AI-based risk engines improve detection accuracy, reduce false positives, and support real-time security enforcement in Zero Trust environments.