A New Decision Tree Ensembles Method for Fake Apps Detection in Android Platform

DOI

10.2991/icmmcce-15.2015.181How to use a DOI?

Keywords

Smartphone Security; Android fake Apps; Feature-based; Ensemble Learning

Abstract

The sharp increase in the number of smartphones makes the fake Apps in Android platform to be an urgent issue. Many approaches have been proposed to defend against these fake Apps. However, most of them have some disadvantage, such as low accuracy, not general, or not robust in big data. This paper proposes an automatic fake Apps detection method by using Decision Tree Ensembles based Detection (i.e., DTED). The DTED is a three-level ensemble method which capitalizes different voting technology. We extract permission features and API calls features relevant to fake Apps behavior by analyzing a large number of samples. Experimental results show that our method achieves accuracy as high as 91.6% and 91.13% F-measure, which performs better than other algorithms in big data.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Huan Ren
AU  - Wei Zhang
AU  - Qingshan Jiang
PY  - 2015/12
DA  - 2015/12
TI  - A New Decision Tree Ensembles Method for Fake Apps Detection in Android Platform
BT  - Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015
PB  - Atlantis Press
SP  - 1252
EP  - 1257
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmcce-15.2015.181
DO  - 10.2991/icmmcce-15.2015.181
ID  - Ren2015/12
ER  -