Utilising Artificial Intelligence in Enhancing Zero-Day Attacks Detection

Agbroko, Mudiaga (2024) Utilising Artificial Intelligence in Enhancing Zero-Day Attacks Detection. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (760kB) | Preview
Preview	PDF (Configuration Manual) Download (6MB) | Preview

Abstract

With the alarming increase in zero-day attacks and the limitations facing current traditional intrusion detection systems, enhancing zero-day attack detection is paramount. This research proposes the use of artificial intelligence algorithms in improving the detection of zero-day attacks. Three supervised machine learning algorithms were employed to evaluate the detection capability of machine learning models compared to traditional intrusion systems. The study was conducted by assessing the performance of Snort, an open-source intrusion detection/prevention system, Decision Tree Classifier, K-Neighbor Classifier, and Random Forest Classifier on the Canadian Institute for Cybersecurity Intrusion Detection Evaluation Dataset (CIC-IDS2017). To improve the performance of the machine learning algorithms, the features were standardised, the dataset’s dimension reduced, and sampling techniques used in attaining a balanced dataset class. The Decision Tree Classifier, K-Neighbor Classifier, and Random Forest Classifier had an accuracy of 0.904, 0.929, and 0.919 respectively. The Decision Tree Classifier had the fastest runtime of 0.006 seconds and the highest processing rate, processing 150,000 entries per second.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mahajan, Kamil 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:	18 Jul 2025 09:00
Last Modified:	18 Jul 2025 09:00
URI:	https://norma.ncirl.ie/id/eprint/8184

Actions (login required)

View Item