Analysis Of DDOS Attack Detection In Cloud Computing Using Machine Learning Algorithm

Abstract

The proliferation of cloud computing has revolutionized the landscape of digital services, offering scalability and flexibility. However, this evolution has also exposed cloud environments to a heightened risk of Distributed Denial of Service (DDoS) attacks, threatening the availability and reliability of hosted services. This research presents a comprehensive analysis of DDoS attack detection in cloud computing, leveraging the capabilities of machine learning algorithms. The study involves the collection and preprocessing of network traffic data within a cloud environment. Relevant features are selected to characterize normal and anomalous activities. Machine learning algorithms, including but not limited to Support Vector Machines (SVM), Random Forests, and Decision Trees, are explored for their efficacy in distinguishing DDoS attacks from legitimate traffic. Furthermore, the research investigates the impact of varying dataset sizes and feature sets on the performance of the detection models.