Volume 2 - Issue 3, May - June 2026

The convergence of Cloud, Fog, and Internet of Things (IoT) technologies has enabled scalable, low-latency, and intelligent distributed systems. However, this integration has significantly expanded the attack surface, exposing systems to sophisticated cyber threats such as distributed denial-of-service (DDoS), botnets, and advanced persistent threats (APTs). Traditional intrusion detection systems (IDS) are inadequate due to their inability to handle dynamic, heterogeneous, and large-scale environments. This paper presents a comprehensive survey of Artificial Intelligence (AI)-driven Intrusion Detection and Prevention Systems (IDPS) in Cloud– Fog–IoT ecosystems. It critically analyzes deep learning, reinforcement learning, and federated learning-based approaches, identifies key limitations, and proposes a novel multi-layer AI-driven IDPS framework. The proposed architecture incorporates distributed intelligence, adaptive learning, and automated mitigation mechanisms to achieve enhanced security, scalability, and real-time responsiveness. Furthermore, this work introduces a hybrid AI model integrating CNN, LSTM, and Deep Reinforcement Learning (DRL), supported by federated learning for privacy preservation. Experimental considerations, research gaps, and future directions are also discussed.

Chethana Ganga N S, "AI-Driven Intrusion Detection and Prevention Framework for Cloud-Fog-IoT Integrated systems:A Comprehensive Review and Future Research Directions" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(3): Page(93-96) May-June 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.