A Method for Automatic Android Malware Detection Based on Static Analysis and Deep Learning

Basit Öğe Kaydı
dc.authoridIbrahim, Mulhem/0000-0002-6285-1500
dc.authoridJasser, Muhammed Basheer/0000-0001-5292-465X
dc.authoridISSA, BAYAN/0000-0002-7559-3416
dc.contributor.authorIbrahim, Mulhem
dc.contributor.authorIssa, Bayan
dc.contributor.authorJasser, Muhammed Basheer
dc.date.accessioned2025-02-20T08:42:15Z
dc.date.available2025-02-20T08:42:15Z
dc.date.issued2022
dc.departmentTürk-Alman Üniversitesien_US
dc.description.abstractThe computers nowadays are being replaced by the smartphones for the most of the internet users around the world, and Android is getting the most of the smartphone systems' market. This rise of the usage of smartphones generally, and the Android system specifically, leads to a strong need to effectively secure Android, as the malware developers are targeting it with sophisticated and obfuscated malware applications. Consequently, a lot of studies were performed to propose a robust method to detect and classify android malicious software (malware). Some of them were effective, some were not; with accuracy below 90%, and some of them are being outdated; using datasets that became old containing applications for old versions of Android that are rarely used today. In this paper, a new method is proposed by using static analysis and gathering as most useful features of android applications as possible, along with two new proposed features, and then passing them to a functional API deep learning model we made. This method was implemented on a new and classified android application dataset, using 14079 malware and benign samples in total, with malware samples classified into four malware classes. Two major experiments with this dataset were implemented, one for malware detection with the dataset samples categorized into two classes as just malware and benign, the second one was made for malware detection and classification, using all the five classes of the dataset. As a result, our model overcomes the related works when using just two classes with F1-score of 99.5%. Also, high malware detection and classification performance was obtained by using the five classes, with F1-score of 97%.
dc.identifier.doi10.1109/ACCESS.2022.3219047
dc.identifier.endpage117352en_US
dc.identifier.issn2169-3536
dc.identifier.scopus2-s2.0-85141617152
dc.identifier.scopusqualityQ1
dc.identifier.startpage117334en_US
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2022.3219047
dc.identifier.urihttps://hdl.handle.net/20.500.12846/1609
dc.identifier.volume10en_US
dc.identifier.wosWOS:000886141300001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherIeee-Inst Electrical Electronics Engineers Inc
dc.relation.ispartofIeee Access
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250220
dc.subjectAndroiden_US
dc.subjectdeep learningen_US
dc.subjectmalwareen_US
dc.subjectmobile securityen_US
dc.subjectstatic analysisen_US
dc.titleA Method for Automatic Android Malware Detection Based on Static Analysis and Deep Learning
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu