Enhancing Network Layer Security in Cloud Computing through Machine Learning Techniques

Chavan, Tejas Shantaram (2024) Enhancing Network Layer Security in Cloud Computing through Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (723kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

In the rapidly evolving landscape of cloud computing, it is necessary to guarantee a robust network layer security system which protects the sensitive user data and thus maintains the integrity and availability of these cloud-based services. This research study explores the application of various advanced machine learning (ML) models in order to detect and reduce any critical vulnerabilities like Distributed Denial of Service (DDoS) attacks, data breaches, and unauthorized access by using the CTU-13 dataset which contains relevant pipeline data including label consolidation, encoding, and balancing techniques. This dataset is used inside these ML models’ training. These ML models include Logistic Regression, Random Forest, XGBoost, and Gradient Boosting Machine (GBM) and they are evaluated for their performance in classifying the network traffic and their ability to discover the malicious activities/patterns. Our results show that the ensemble-based models i.e. Random Forest, XGBoost, and GBM have significantly outperformed the baseline Logistic Regression model. These ensemble-based models, especially the Random Forest, achieved accuracy exceeding 99% and low False Positive Rates (FPR). These findings show the potential of such ML techniques in enhancing the security posture of these cloud environments i.e. for both individual and enterprise needs. In this research study, it is also discussed that there are trade-offs between model complexity and computational efficiency which gives better insights into the practical deployment of these models. This study concludes by pointing out the various key areas for future research like the integration of ML with blockchain and homomorphic encryption. This research contributes to the research community for the intelligent security frameworks in the cloud computing infrastructures which can handle the complex world of cyber-attacks.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Kazmi, Aqeel UNSPECIFIED
Uncontrolled Keywords:	Cloud Computing; Network Security; Machine Learning; DDoS Attacks; Data Breaches; Unauthorized Access; Random Forest; XGBoost; Gradient Boosting Machine; Logistic Regression; CTU-13 Dataset
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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:	14 Jul 2025 15:19
Last Modified:	14 Jul 2025 15:19
URI:	https://norma.ncirl.ie/id/eprint/8090

Actions (login required)

View Item