Exploring the use of Explainable AI for improving intrusion detection systems

Singh, Ravi Ranjan (2024) Exploring the use of Explainable AI for improving intrusion detection systems. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (792kB) | Preview
Preview	PDF (Master of Science) Download (517kB) | Preview

Abstract

The aim and objectives of this research therefore lies in the proposition of a solution to the global challenge of enhancing IDSs through the employment of deep ML classifiers as Random Forest, Support Vector Machine, or Multi-Layer Perceptron. SVM was found to have an accuracy of 82% with comparable precision and recall making it superior to all models in this study. On the other hand, MLP detected 95% of the time for malicious traffic and achieved the highest accuracy of 84% in differentiating benign traffic. In order to ensure that outputs are clearly and transparently interpretable, this study highlighted the features responsible for critical decisions about model selections with SHAP and LIME. The findings highlight that intrusion detection system facilitated through the integration of artificial intelligence significantly enhances cybersecurity through the delivery of trusted and explainable intrusion detection services. Areas that may be explored in future research so as to increase efficacy include real time monitoring and ideal model configurations.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Prior, Michael UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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 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 Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	28 Jul 2025 11:10
Last Modified:	28 Jul 2025 11:10
URI:	https://norma.ncirl.ie/id/eprint/8258

Actions (login required)

View Item