Detecting Malicious Content from Extracted API Call Sequence by Applying Deep Learning and Machine Learning Algorithm

Gerard, Aleena (2020) Detecting Malicious Content from Extracted API Call Sequence by Applying Deep Learning and Machine Learning Algorithm. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (771kB) | Preview
Preview	PDF (Configuration manual) Download (677kB) | Preview

Abstract

Nowadays, the growth of malware is increasing exponentially in variance and numbers parallelly with the expansion of digital world. In cybersecurity field malware has become the major issue and many attempts of work has been contributed to this field. Machine learning algorithms has been used for the detection of malware as it can identify obscure patterns in big datasets. Deep learning algorithms has potential varied layers which overcomes the limitations of machine learning algorithms as it provides high accuracy in classification in various domains. For the detection, API call sequences provides information about the behavioural attributes in a program. The goal of this research is to classify and detect malware from a high dimensional API call sequences dataset using deep learning algorithms like CNN, RNN and LSTM. The performance of these algorithms is being compared with traditional machine learning algorithms like LR, LDA, KNN, DT, NB with the same high dimensional dataset. This implementation and comparison study results in 98 percent of accuracy for both deep learning and machine learning algorithm.

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:	26 Jan 2021 15:36
Last Modified:	26 Jan 2021 15:36
URI:	https://norma.ncirl.ie/id/eprint/4492

Actions (login required)

View Item