Enhancing DevOps Continuous Monitoring Phase: Hybrid Intrusion Detection and Ensemble Learning System (HIDELS)

Abstract

Companies are excited to maintain high-quality software while reducing the costs of production. DevOps is a contemporary software development life cycle paradigm in which development and operations teams join together during all stages of software development. Nonetheless, security is inadequately integrated inside DevOps. Although there have been attempts to amalgamate security with DevOps, resulting in the emergence of DevSecOps, considerable progress is necessary. The aim of Hybrid Intrusion Detection and Ensemble Learning System (HIDELS) is to present the incorporation of intrusion detection into the continuous monitoring phase of DevOps, hence enhancing DevSecOps. The integration comprises five machine learning (ML) models and assesses the performance of each model independently. Subsequently, the models are consolidated into an ensemble learning (EL) framework to improve overall robustness and provide more stable predictive outcomes. The results of the individual models show the decision tree (DT) classifier outperforming all the remaining models in terms of accuracy, precision, recall, and f1-score, with 99.5%, 99.5%, 99.7%, and 99.6% on average. Conversely, the EL model attained an average of 99.4%, 99.6%, 99.7%, and 99.7% for accuracy, precision, recall, and F1-score, respectively, exceeding the performance of all other individual ML models.