Android Malware Detection Using Autoencoder
This addresses the problem of malware spread on Android devices for users and researchers, but it appears incremental as it applies an existing method (Autoencoder) to this domain.
The paper tackles Android malware detection by proposing a deep learning approach that uses Autoencoder on five feature sets, achieving high accuracy in identifying malware.
Smartphones have become an intrinsic part of human's life. The smartphone unifies diverse advanced characteristics. It enables users to store various data such as photos, health data, credential bank data, and personal information. The Android operating system is the prevalent mobile operating system and, in the meantime, the most targeted operating system by malware developers. Recently the unparalleled development of Android malware put pressure on researchers to propose effective methods to suppress the spread of the malware. In this paper, we propose a deep learning approach for Android malware detection. The proposed approach investigates five different feature sets and applies Autoencoder to identify malware. The experimental results show that the proposed approach can identify malware with high accuracy.