Cloud-based Intrusion Detection System using Various Machine Learning Techniques

Abstract

The growing popularity of cloud computing demands robust security measures. In the context of machine learning, this research work represents a novel method for enhancing cloud intrusion detection by integrating Deep Neural Networks (DNNs) with the Random Forest (RF) algorithm. The well-known NSL-KDD dataset, a benchmark dataset for intrusion detection systems, is the subject of this research study. By utilizing DNNs' feature extraction skills and the RF algorithm's interpretability and ensemble characteristics, the study shows how effective the suggested method is at precisely recognizing and classifying different kinds of intrusions in cloud computing environments. The study also shows that the proposed DNN-RF model, which performs better than either model alone, specifying that it has the prospective to be used for real-time intrusion detection in cloud-based systems. The results underline how critical it is to use cutting-edge machine learning techniques to fortify cloud environments' security infrastructure, thereby lowering possible risks and protecting the integrity and confidentiality of sensitive data.