Machine Learning Techniques for Cloud-Based DDoS Attack Detection: A Comprehensive Survey

Abstract

Cloud computing environments are rapidly vulnerable to Distributed Denial of Service (DDoS) attacks, which interrupt the services by flooding them with illegitimate traffic and denying access to genuine users [1]. The Existing DDOS detection mechanisms, depends on fixed rules or known attack patterns, often fail to cope with the dynamic and large-scale nature of cloud networks. In this work, a machine learning-based framework is presented to support the detection of DDoS attacks through the analysis of network traffic patterns in a cloud environment. The proposed approach combines traffic monitoring with supervised learning techniques to classify normal and malicious traffic. This method will help to adapt, detect attacks, and keep the cloud services available. Future work will test the system in real conditions, use it across different clouds, and improve it with smarter learning methods to handle new attacks.