Machine Learning Approaches for Malware Classification in Android Platform: A Review

Authors

  • Howida Alkaaf Faculty of Computing, Universiti Teknologi Malaysia, 81310 Johor Bahru, Johor, Malaysia
  • Farkhana Muchtar Faculty of Computing, Universiti Teknologi Malaysia, 81310 Johor Bahru, Johor, Malaysia
  • Salmah Fattah Faculty of Computing and Informatics, Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu, Sabah, Malaysia
  • Asraf Osman Ibrahim Elsayed Faculty of Computing and Informatics, Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu, Sabah, Malaysia
  • Carolyn Salimun Faculty of Computing and Informatics, Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu, Sabah, Malaysia
  • Hadzariah Ismail Faculty of Computing and Informatics, Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu, Sabah, Malaysia
  • Farhan Masud Department of Statistics and Computer Science, University of Veterinary and Animal Sciences, Lahore, Pakistan

DOI:

https://doi.org/10.37934/araset.48.1.248268

Keywords:

Android application, Android malware, Machine learning

Abstract

The rapid growth of Android applications has led to a continuous influx of Android malware. Numerous research has been undertaken to tackle that issue. Existing research has indicated that leveraging machine learning is a highly effective and promising approach for Android malware detection. This paper presents a review of Android malware detection methodologies that rely on machine learning. We commence by providing a brief overview of the background context related to Android applications, including insights into the Android system architecture, security mechanisms, and the categorization of Android malware. Subsequently, with machine learning as the central focus, we methodically examine and condense the current state of research, encompassing crucial perspectives such as sample acquisition, data pre-processing, feature selection, machine learning models, algorithms, and the assessment of detection effectiveness. The aim of this review is to equip scholars with a holistic understanding of Android malware detection through the lens of machine learning. It is intended to serve as a foundational resource for future researchers embarking on new endeavours in this field, while also providing overarching guidance for research endeavours within the broader domain.

Downloads

Download data is not yet available.

Author Biographies

Howida Alkaaf, Faculty of Computing, Universiti Teknologi Malaysia, 81310 Johor Bahru, Johor, Malaysia

howida10@gmail.com

Farkhana Muchtar, Faculty of Computing, Universiti Teknologi Malaysia, 81310 Johor Bahru, Johor, Malaysia

farkhana@utm.my

Salmah Fattah, Faculty of Computing and Informatics, Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu, Sabah, Malaysia

salmahf@ums.edu.my

Asraf Osman Ibrahim Elsayed, Faculty of Computing and Informatics, Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu, Sabah, Malaysia

ashrafosman@ums.edu.my

Carolyn Salimun, Faculty of Computing and Informatics, Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu, Sabah, Malaysia

carolyn@ums.edu.my

Hadzariah Ismail, Faculty of Computing and Informatics, Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu, Sabah, Malaysia

had@ums.edu.my

Farhan Masud, Department of Statistics and Computer Science, University of Veterinary and Animal Sciences, Lahore, Pakistan

fmasud@uvas.edu.pk

Published

2024-07-10

Issue

Section

Articles

Most read articles by the same author(s)