A Machine Learning-Based Intrusion Detection System for Monitoring Virtualized Cloud Networks

Abstract

The increasing prevalence of cloud computing has brought significant scalability and efficiency to IT infrastructure but has also exposed systems to new and sophisticated security threats. This paper presents a machine learning-based intrusion detection system (IDS) tailored for virtualized cloud environments. By leveraging supervised learning models such as Support Vector Machines (SVM), Random Forests (RF), and Artificial Neural Networks (ANN), the system classifies and detects malicious traffic patterns with high accuracy. Emphasis is placed on minimizing false positives and ensuring scalability across virtual networks. Empirical results on benchmark cloud datasets demonstrate that our proposed system achieves superior detection rates compared to traditional signature-based methods.