Deep Learning-Driven Real-Time Intrusion Detection System for Cloud-Based Database Management Systems

Abstract

The Cloud-based Database Management Systems (CDBMS) have become essential for modern data storage and processing, but they are increasingly exposed to advanced cyber threats. Ensuring real-time security in such environments is a critical challenge. This paper presents a Deep Learning-Driven Real-Time Intrusion Detection System designed to enhance the protection of cloud-based databases. The proposed system utilizes deep learning models to analyze network traffic and detect anomalies indicative of potential intrusions. By enabling continuous monitoring and intelligent classification, the system improves detection accuracy while reducing false positives. Experimental analysis demonstrates that the proposed approach outperforms traditional methods in identifying both known and unknown attacks. The model’s adaptability and scalability make it suitable for dynamic cloud environments, thereby strengthening overall database security and reliability.