Evaluation of Intrusion Detection System based on Gaussian Mixture and K-Means Clustering with Random Forest Classifier

Pradhan, Bivor (2020) Evaluation of Intrusion Detection System based on Gaussian Mixture and K-Means Clustering with Random Forest Classifier. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (498kB) | Preview
Preview	PDF (Configuration manual) Download (267kB) | Preview

Abstract

During the recent years there has been a sharp increase in the number of internet users which has consequently increased the data transmitted through the network. As the network continue to scale to the rising demand, they have become vulnerable to frequent attacks from malicious actors. Timely detection and mitigation of such threat is vital and necessary to maintain a stable and safe environment. Intrusion detection system (IDS) play a vital role in the detection of such attacks from external sources. Various approaches have been proposed and deployed to develop an efficient and effective IDS. Yet the developing a perfect IDS is still a challenge with the advanced attack strategies that create novel types of attacks. This paper explores the combination of unsupervised and supervised machine learning algorithms in developing an effective IDS with low false alarm rate. Performance metrics such as Accuracy, False Alarm Rate, Detection Rate, Precision and F1 score are considered to evaluate the results.
Keywords: IDS, K-Means Clustering, Gaussian clustering, Random Forest

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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:	Dan English
Date Deposited:	27 Jan 2021 18:15
Last Modified:	27 Jan 2021 18:15
URI:	https://norma.ncirl.ie/id/eprint/4515

Actions (login required)

View Item