Volume 11 - Issue 2
De-LADY: Deep learning based Android malware detection using Dynamic features
- Vikas Sihag
Sardar Patel University of Police, Security and Criminal Justice, Jodhpur, India, National Institute of Technology, Raipur, India
vikas.sihag@policeuniversity.ac.in
- Manu Vardhan
National Institute of Technology, Raipur, India
mvardhan.cs@nitrr.ac.in
- Pradeep Singh
National Institute of Technology, Raipur, India
psingh.cs@nitrr.ac.in
- Gaurav Choudhary
School of Computing Science and Engineering ,VIT Bhopal University, Bhopal, Madhya Pradesh
gauravchoudhary7777@gmail.com
- Seiil Son
Korea Communication Agency, South Korea
seiilson@kca.kr
Keywords: Android, Malware detection, Code obfuscation, Familial classification
Abstract
Popularity and market share of Android operating system has given significant rise to malicious apps
targeting it. Traditional malware detection methods are obsolete as current malwares are equipped
with state of the art obfuscation methods to hide their intent from scanning engines. In this paper,
we propose De-LADY (Deep Learning based Android malware detection using DYnamic features)
an obfuscation resilient approach. It utilizes behavioral characteristics from dynamic analysis of an
application executed in emulated environment. The proposed approach is evaluated against 13533
applications from categories such as banking, gaming and utilities. De-LADY is effective with 98.08%
detection rate and 98.84% F-measure. Furthermore, it outperformed existing machine learning approaches