An Efficient Intrusion Detection Solution for Cloud Computing Environments Using Integrated Machine Learning Methodologies

Abstract

Cloud computing provides a range of services over the Internet using a pay-per-use model. Consequently, several firms have already used this system to entice people with its appealing characteristics. However, its architecture renders it susceptible to malicious assaults. This necessitates the implementation of an Intrusion Detection System (IDS) that can identify such assaults in a cloud environment accurately. This study presents a Machine Learning Efficient Intrusion Detection System (ML-EIDS) that integrates a Fuzzy C Means (FCM) clustering method with a Support Vector Machine (SVM) to enhance the precision of the detecting method in a cloud computing scenario. The suggested ML-EIDS system has been executed and contrasted with preexisting methods. The NSL-KDD dataset is used for conducting experiments. Through performance assessment and comparative analysis, the findings achieved by implementing the ML-EIDS hybrid method demonstrate that the suggested system can accurately detect abnormalities with high precision and a low occurrence of false alarms, surpassing current methodologies.