Windows Portable Executor Malware detection using Deep learning approaches

Parmar, Yogesh Bharat (2020) Windows Portable Executor Malware detection using Deep learning approaches. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Malware’s are the main barriers in the growth of digital acceptance. Every system or device in the world is connected with the internet and internet became the main source of spreading malware’s. In the windows operating system various types of malware’s are found, detection of such malware in timely manner is a challenging task. Almost every executive file in the windows operating system is in the PE (Portable Executor) format. PE file begins with the header that includes the various information about the file such as type of application, space requirement, libraries used and many more. Our main goal, in this work is to detect the windows malware without relying on any explicit signature based methods. In order to solve such issues, we are using different types of deep neural networks. CNN, RNN and CONV-LSTM models are used in order to detect the malicious behaviour from the Portable executable samples. The target value can be either malicious or legit. The classification results of every model will be analysed and compared using different classification metrics and achieved a highest classification accuracy of 94.18% using CONV-LSTM model.

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 17:47
Last Modified:	27 Jan 2021 17:47
URI:	https://norma.ncirl.ie/id/eprint/4510

Actions (login required)

View Item