DETEKSI MALWARE ANDROID MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)

HIDAYATULLAH, HIDAYATULLAH and Stiawan, Deris (2024) DETEKSI MALWARE ANDROID MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011182025024.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10MB) | Request a copy
	Text RAMA_56201_09011182025024_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10MB) | Request a copy
	Text RAMA_56201_09011182025024_0003047905_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (3MB)
	Text RAMA_56201_09011182025024_0003047905_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (476kB) | Request a copy
	Text RAMA_56201_09011182025024_0003047905_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (332kB) | Request a copy
	Text RAMA_56201_09011182025024_0003047905_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (828kB) | Request a copy
	Text RAMA_56201_09011182025024_0003047905_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (193kB) | Request a copy
	Text RAMA_56201_09011182025024_0003047905_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (171kB) | Request a copy
	Text RAMA_56201_09011182025024_0003047905_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy

Abstract

As the most widely used mobile operating system, Android is increasingly becoming a prime target for malware attacks. The popularity of this operating system makes it attractive for cyber security criminals to steal valuable data, one of which is by installing Android malware applications. Several studies have used various Machine Learning (ML) methods to recognize Android malware applications from benign applications. However, this method is not able to detect newer and more sophisticated Android malware applications. Therefore, this research presents a Deep Learning (DL) approach to detect Android malware applications using the Convolutional Neural Network (CNN) method. Experiments were conducted and tested on 20,000 malware applications and 9,999 benign applications using 173 permission features taken from the applications. This research includes several performance metrics such as accuracy, precision, recall, f1-score in identifying the classifier with the best performance. The dataset was also oversampled to overcome imbalanced data. At the end of the study, the results showed that detecting malware applications on the Android operating system using the CNN method achieved an accuracy of 99.99%, with a precision of 99.98%, a recall of 100% and an f1-score of 99.99% with the best error value of 0.0054%. The performance results observed from this model are better than the results reported in previous research on machine learning and deep learning based Android malware detection

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Android Malware Detection, Malware, Deep Learning, Permission, Convolutional Neural Network
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Hidayatullah Hidayatullah
Date Deposited:	27 Jun 2024 05:10
Last Modified:	27 Jun 2024 05:10
URI:	http://repository.unsri.ac.id/id/eprint/148194

Actions (login required)

View Item