RANK: AI-ASSISTED END-TO-END ARCHITECTURE FOR DETECTING PERSISTANT ATTACKS IN ENTERPRISE NETWORKS

Abstract

Enterprise networks continue to face sophisticated and persistent cyber attacks that evolve rapidly and evade traditional security mechanisms. To address these challenges, this study proposes RANK, an AI-assisted end-to-end detection architecture designed to identify, correlate, and analyze persistent threats across large-scale network environments. The architecture integrates machine learning–based anomaly detection, automated threat correlation, and continuous monitoring to provide a comprehensive view of network behavior. By combining multiple data sources—such as network traffic, host activity, and behavioral patterns—RANK enhances early detection of stealthy attacks and reduces false positives. The system leverages adaptive learning models that improve detection accuracy over time while supporting real-time alerting and scalable deployment. Overall, RANK demonstrates a more intelligent, resilient, and efficient approach to safeguarding enterprise networks against persistent cyber threats.