A Hybrid Classifier based on Machine Learning Algorithms for Intrusion Detection in Cloud Computing

Abstract

Cloud computing systems are susceptible to various types of attacks that can compromise their security. The system experiences a degradation in performance with respect to its integrity, confidentiality, and security. The introduction of an Intrusion Detection System has been proposed as a solution to address the aforementioned issues. This system is designed to identify various types of attacks, including but not limited to Normal Probe, DDoS, and R2L attacks. The present study proposes a hybrid classification approach for the development of an intrusion detection system. The hybrid clustering approach for intrusion detection has been proposed with the aim of effectively categorizing various types of attacks. This study introduces two innovative algorithms, namely the attack clustering algorithm and the machine learning and deep learning classifier, which are referred to as DBN (Deep Belief Networks), Random Forest, and Naïve Bayes. All of the models under consideration are deemed acceptable, and the research methodology employed yields an effective intrusion detection and prevention system for mitigating security breaches and intruder attacks