NORMA eResearch @NCI Library

A new approach to Cloud security posture management and anomaly detection in cloud traffic using gradient boosting classifier algorithm

Doddakarade Nagendra, Varun Gowda (2023) A new approach to Cloud security posture management and anomaly detection in cloud traffic using gradient boosting classifier algorithm. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (511kB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (277kB) | Preview

Abstract

Cloud Security Posture Management is a set of practices and tools designed to ensure the consistent and effective security configuration of cloud resources that involves monitoring, assessing, and managing the security posture of an organization’s cloud infrastructure to prevent and address security misconfigurations, vulnerabilities, and compliance issues. This project navigates the area of cloud security with a dual focus on fortifying the security posture and detecting anomalies within cloud traffic. A conceptual security framework is devised by integrating features from prominent cloud security frameworks. This framework serves as a comprehensive guide for managing security postures in the cloud.

Simultaneously, the study delves into anomaly detection in cloud traffic, employing the Gradient Boosting Classifier algorithm to discern deviations from established norms. Rigorous preprocessing, feature selection, and model training characterize the methodology. Applying the proposed conceptual framework and the gradient boosting classifier aligns with the dynamic nature of cloud computing environments, ensuring robust security measures and efficient identification of anomalous activities. The model achieved an accuracy of 94.57% and 96% of the F1-score, which is better when compared to the SVM (89%) and LSTM (94%) models. These evaluation factors showcase the efficacy of the approach in enhancing cloud security resilience, offering a substantial contribution to the evolving landscape of cloud security management.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Sahni, Vikas
UNSPECIFIED
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 > Algebra > Algorithms > Computer algorithms
Q Science > QA Mathematics > Computer software > Computer Security
T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Ciara O'Brien
Date Deposited: 16 Apr 2025 11:22
Last Modified: 16 Apr 2025 11:22
URI: https://norma.ncirl.ie/id/eprint/7431

Actions (login required)

View Item View Item