AI-Enhanced Cybersecurity: Machine Learning for Anomaly Detection in Cloud Computing
Priya Thapa
Department of Information Technology, Mid-Western University, Nepal
Tamilselvan Arjunan
Keywords: Cloud Computing, Cybersecurity, Anomaly Detection, Machine Learning, Threat Monitoring, Attack Patterns
Abstract
Cloud computing has become ubiquitous, providing convenient on-demand access to computing resources. However, security remains a major concern, as cloud environments are increasingly targeted by cyber-attacks. Here, we review the use of machine learning techniques for anomaly detection to enhance cybersecurity in cloud computing. We provide background on cloud computing architectures, cyber threats, and anomaly detection. We then comprehensively survey state-of-the-art machine learning methods for anomaly detection in cloud environments, including supervised, unsupervised, and hybrid approaches. Specific techniques covered include neural networks, support vector machines, clustering, and ensemble methods. We analyze the strengths and limitations of these techniques and provide recommendations for selecting appropriate algorithms based on factors like labeled data availability and detection goals. Challenges and open research questions in deploying machine learning for cloud security are discussed. We argue that AI-enhanced anomaly detection has excellent potential to identify novel attack patterns and improve resilience against continually evolving threats. Our analysis aims to provide guidance for researchers and practitioners developing the next generation of intelligent cyberdefense systems.
Author Biography
Tamilselvan Arjunan
