An Ensemble Machine learning approach for the prediction of vulnerabilities leading to DOS – Attacks on Cloud applications

Abstract

Cloud computing is pivoting the landscape of digital technologies with a vast amount of migration by businesses to ensure flexibility and adaptation to changing work demands. Vulnerabilities in cloud applications pose a significant challenge especially the ones leading to Denial of service (DOS) attacks. This work leverages on the use of an ensemble-based Machine learning model for predicting the vulnerabilities inherent within the software-as-a-service (SAAS) layer of the cloud. The model was trained and tested on source data of the National vulnerability database and validated using standard metrics to evaluate its performance and ability to predict new vulnerabilities. The results yielded a higher performance of the ensemble model than the single classification algorithms.