AI-Enhanced Cloud Security: A Dynamic Framework for Adaptive Threat Intelligence
Kateřina Malá, M R Yadhukrishna, B Jyothi, M. Pradeep · 2025
The rapidly evolving cyber threat landscape necessitates dynamic and intelligent approaches to cloud security. This research highlights the transformative role of Artificial Intelligence (AI) in addressing the inadequacies of traditional static rule-based systems for threat detection. By integrating advanced techniques like Extended Detection and Response (XDR), Security Information and Event Management (SIEM), Security Orchestration, Automation, and Response (SOAR), and Network Detection and Response (NDR), AI-driven systems enhance real-time monitoring and network forensics, enabling faster and more accurate incident responses. The proposed framework combines supervised learning with Random Forest for identifying known threats and unsupervised learning with Isolation Forest for detecting novel anomalies. It utilizes AI- driven anomaly detection and machine learning (ML) techniques to adapt to emerging security challenges. Moreover, this research emphasizes the synergy between AI and cloud security operations, showcasing how AI accelerates incident response times while fortifying organizational defences against sophisticated attacks. By refining proactive measures and leveraging continuous data analysis from diverse cloud environments, this study offers a robust, scalable approach to safeguarding cloud infrastructures. The findings underline the necessity of adopting AI-powered strategies to maintain a flexible and resilient security posture in an era of increasingly complex cyber threats.