PERMISSION BASED ANDROID MALWARE DETECTION USING MACHINE LEARNING
International Journal of Fundamental and Applied Sciences (IJFAS) · 2021
DOI: 10.59415/ijfas.v10i1.229 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Fundamental and Applied Sciences (IJFAS), 2021. Verfasst von Sonal Pandey und 2 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben.
Abstract (Originalsprache)
Due to the open architecture of the Android operating system, there has also been a huge increase in mobile malware. With the growth in amount, variants, diversity and sophistication in malware, conventional methods often fail to detect malicious applications. Signatures based technologies work efficient for known malware but fail to detect unknown or new malware. In this paper author will appliance an approach to detect the unfamiliar Android malware using machine learning techniques. In our approach, we extract permissions (AOSP and third party permissions) features for getting high accuracy. Then features were selected along with separate apks (malware and benign files) in training and testing classifiers. We evaluate our method on AndroZoo dataset (15000 malware and 15000 benign Apks) We use Random forest classifiers for classification of Android malware and achieved 91.1% accuracy with AOSP and 72.3% accuracy with Third Party Permission.
Zitieren
APA
Pandey, S., Satyasheel, & Jain, D. (2021). PERMISSION BASED ANDROID MALWARE DETECTION USING MACHINE LEARNING. International Journal of Fundamental and Applied Sciences (IJFAS). https://doi.org/10.59415/ijfas.v10i1.229
Vancouver
Pandey S, Satyasheel, Jain D. PERMISSION BASED ANDROID MALWARE DETECTION USING MACHINE LEARNING. International Journal of Fundamental and Applied Sciences (IJFAS). 2021. doi:10.59415/ijfas.v10i1.229
BibTeX
@article{Pandey2021,
author = {Pandey, Sonal and Satyasheel and Jain, Diksha},
title = {PERMISSION BASED ANDROID MALWARE DETECTION USING MACHINE LEARNING},
journal = {International Journal of Fundamental and Applied Sciences (IJFAS)},
year = {2021},
doi = {10.59415/ijfas.v10i1.229}
}
EUVIMED