Can Semi Supervised Feature Selection improve Ransomware Detection

Smyth, Gavin (2022) Can Semi Supervised Feature Selection improve Ransomware Detection. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (973kB) | Preview
Preview	PDF (Configuration manual) Download (814kB) | Preview

Abstract

Today, ransomware is one of the most harmful cybersecurity threats that organizations and people face especially with the expanse of organisations attack surface with employees working remotely. Machine learning has proven to be extremely helpful in ransomware detection, although, this requires a huge amount of labelled data for training and categorizing data takes time and money. However, there is a huge amount of unlabelled data. Semi-supervised learning, which uses a small number of labelled data and a large number of unlabelled data for learning, can be used to address this issue. This also encourages academics to create semi-supervised feature selection techniques that assesses feature relevance using both labelled and unlabelled data. Although researchers have proposed a variety of feature selection methods combined with Semi Supervised learning, this paper attempts to analyse different Semi Supervised feature selection and semi-supervised classification methods applied to the CICAndMal 2017 dataset. Semi JMI, Semi MIM and Semi IAMB were applied to different Semi Supervised classification models and the accuracy measured. Analysis on the subsets determine that Semi JMI outperformed Semi MIM and Semi IAMB with an average accuracy of 85% when datasets are balanced and again Semi JMI performed on the Overall dataset with an average accuracy of 73%. Therefore, Semi Supervised feature selection combined with Semi Supervised classification methods can be considered for future research in detecting ransomware.

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 Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Tamara Malone
Date Deposited:	05 Jan 2023 15:38
Last Modified:	07 Mar 2023 12:10
URI:	https://norma.ncirl.ie/id/eprint/6062

Actions (login required)

View Item