An Efficient Investigation of Cloud Computing Security with Machine Learning Algorithm

Due to developments in technologies like Cloud Computing (CC), the Internet of Things (IoT), etc., the data volume transmitted across communication infrastructures has skyrocketed recently. In order to make network systems susceptible, attackers have increased their determinations. Improving the security of such network systems is very crucial. Using Deep Learning (DL) methods with an Intrusion Detection System (IDS) framework is put into action in this research. The Gated Recurrent Unit (GRU) as well as Support Vector Machine (SVM) are used in this study for attack detection. Therefore, the implementation of SoftMax in the GRU model's last output layer, this study introduces a linear SVM. The NSL-KDD dataset is taken into account to evaluate the proposed IDS framework's performance. In addition, when the number of features increases, current IDSs have poor test accuracy ratings when it comes to identifying new attacks. Each dataset's feature space was reduced using an XGBoost (XGB)-based feature selection approach in this research. After that, 22 detailed characteristics were selected from the NSL-KDD dataset using XGB. The results show that, the proposed IDS paradigm outperformed other approaches.