KLASIFIKASI MALWARE BERDASARKAN FITUR API CALL DAN ANDROID PERMISSIONS MENGGUNAKAN RADIAL BASIS FUNCTION

Bagas Aditya Wibisono, . (2022) KLASIFIKASI MALWARE BERDASARKAN FITUR API CALL DAN ANDROID PERMISSIONS MENGGUNAKAN RADIAL BASIS FUNCTION. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

	Text ABSTRAK.pdf Download (15kB)
	Text AWAL.pdf Download (883kB)
	Text BAB 1.pdf Download (34kB)
	Text BAB 2.pdf Restricted to Repository UPNVJ Only Download (871kB)
	Text BAB 3.pdf Restricted to Repository UPNVJ Only Download (291kB)
	Text BAB 4.pdf Restricted to Repository UPNVJ Only Download (643kB)
	Text BAB 5.pdf Download (17kB)
	Text DAFTAR PUSTAKA.pdf Download (19kB)
	Text RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (13kB)
	Text LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB)
	Text ARTIKEL KI.pdf Restricted to Repository staff only Download (445kB)
	Text HASIL_PLAGIARISME.pdf Restricted to Repository staff only Download (12MB)

Abstract

Malware has become a major threat to technology users today. Malware or Malicious Software is intrusive software with the purpose of infecting, browsing, stealing, or damaging a device. Various malware detection methods have been developed to anticipate the development of malware. This study focuses on malware classification based on API calls and Android permissions using Radial Basis Function Network with K-Means Clustering as the centroid selection method. Radial Basis Function Network is part of an artificial neural network that uses a Gaussian function as its activation function, while K-Means Clustering is an unsupervised learning algorithm in machine learning or clustering algorithms. The dataset used is malgenome-215-dataset which can be downloaded from the figshare repository. Data split is done with K-Fold. The tests were carried out based on the hyperparameters of the learning rate, the number of epochs, the number of hidden units, and the number of K in the K-Fold. Accuracy, precision, recall, and F1 scores were calculated based on the confusion matrix. The experimental results showed 98.41% accuracy, 99.3% precision, 97.92% recall, and 98.6% F1 score.

Item Type:	Thesis (Skripsi)
Additional Information:	[No. Panggil: 1810511075] [Pembimbing 1: Didit Widiyanto] [Pembimbing 2: Noor Falih] [Penguji 1: Henki Bayu Seta] [Penguji 2: Nurul Chamidah]
Uncontrolled Keywords:	Malware Classification, API call, Android Permissions, Radial Basis Function Network, K-Means Clustering
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User:	Bagas Aditya Wibisono
Date Deposited:	26 Jul 2022 07:42
Last Modified:	26 Jul 2022 08:02
URI:	http://repository.upnvj.ac.id/id/eprint/19586

Actions (login required)

View Item