A Cloud-Based Network Intrusion Detection System using Hybrid Ensemble Machine Learning and Explainable AI

Gadhepally, Bhargavi (2025) A Cloud-Based Network Intrusion Detection System using Hybrid Ensemble Machine Learning and Explainable AI. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (986kB) | Preview
Preview	PDF (Configuration Manual) Download (98kB) | Preview

Abstract

Cloud computing has increased the complexity and scale of modern network infrastructures by making them more vulnerable to complex cyber-attacks that traditional rule-based intrusion detection systems fail to detect. This study solves the challenge of achieving accurate, low-latency and interpretable network intrusion detection in cloud environments. The main objective of this study is to design and evaluate a cloud-based Network Intrusion Detection System (NIDS) that improves attack classification accuracy while maintaining transparency and practical deployment. To achieve this a hybrid ensemble machine learning approach where XGBoost as a meta- classifier. The system has been trained and evaluated with SMOTE which applied to reduce class imbalance. Explainable AI has been integrated using LIME to provide local, feature-level explanations for intrusion predictions. The proposed system has been implemented and evaluated in an AWS cloud environment by considering both detection performance and operational metrics. Experimental results has been shown that the hybrid ensemble model outperforms individual classifiers by achieving 90%accuracyand macro F1-score while handling overlapping attack patterns. The use of LIME enhances model interpretability by aligning with current state-of-the-art trends inexplainable security analytics. Future work will focus on real-time traffic analysis and further optimization for edge-cloud environments.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Emani, Sai UNSPECIFIED
Uncontrolled Keywords:	Network Intrusion Detection; Hybrid Ensemble Learning; Cloud; Latency
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	31 Aug 2026 14:13
Last Modified:	31 Aug 2026 14:13
URI:	https://norma.ncirl.ie/id/eprint/9700

Actions (login required)

View Item