Detection of Zero-day Malware Using Hybrid Supervised and Un-supervised Machine Learning Algorithms

Choudhry, Mohammed Mustafa Raza (2022) Detection of Zero-day Malware Using Hybrid Supervised and Un-supervised Machine Learning Algorithms. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

Malware is one of the main dangers for the present figuring world from the number of various sites circulating malicious application is expanding at very fast rate. Malware examination and anticipation strategies can be progressively used to becoming vital for PC frameworks associated with the Internet. This product tries to gain advantage of the framework's weaknesses and security breach to take significant data without the client's information, and covertly send it to distant servers constrained by assailants. Generally, antimalware items used for marking and identifying known malware. In any case, the mark-based strategy doesn't scale well in distinguishing muddled and stuffed malware. Taking into account that the reason for a issue is regularly best perceived by the concentrating on the primary parts of a code likewise the mental aides, guidance opcode as well as API Call, and so forth In this paper, we have researched the pertinence of the highlights of unloaded vindictive with harmless executables like memory helpers, guidance opcodes, and API to distinguish a component that characterizes the executable. Trials were directed on two datasets utilizing AI and profound learning approaches like Random Forest (RF), KNN, Logistic Regression, Naïve Bayes, Decision Tree. The learning strategies and showed a tweaked profound neural organization that brought about a accuracy of 99.72% and 99.37% on UCI Malware and Virus Share Dataset, individually.

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:	Clara Chan
Date Deposited:	30 Nov 2022 19:38
Last Modified:	30 Nov 2022 19:38
URI:	https://norma.ncirl.ie/id/eprint/5950

Actions (login required)

View Item