Enhancing Cloud Data Center Security through Deep Learning: A Comparative Analysis of RNN, CNN, and LSTM Models for Anomaly and Intrusion Detection
Shimaa A. Ahmed, Entisar H. Khalifa, Majid Nawaz, Faroug A. Abdalla, Ashraf F. A. Mahmoud
Abstract
Cloud data centers form the backbone of modern digital ecosystems, enabling critical operations for businesses, governments, and individuals around the world. However, their high connectivity and complexity make them prime targets for cyberattacks, leading to service disruptions and data breaches. This paper investigates the use of deep learning techniques, namely Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), and Long Short-Term Memory (LSTM) networks, to enhance cloud data center security. By employing these models for anomaly detection and intrusion prevention, the study performs a comparative analysis. The results indicate that the LSTMs achieved the highest ROC AUC score (0.90), demonstrating better detection of persistent threats. These findings highlight the potential of deep learning to revolutionize cloud security by providing scalable, accurate, and proactive measures against evolving cyber threats.