A Novel Android Application Penetration Analysis Method

DOI

10.2991/jimec-17.2017.6How to use a DOI?

Keywords

Android application; defect analysis; penetration test

Abstract

As the Android craze spread through the world, even the rapid development of mobile technology can not prevent applications from vulnerability abuse. The existing detection system mostly applied static analysis techniques to single application, which make a limited standard of accuracy and efficiency. In this work, we propose a novel penetration model. First of all, we categorize the Android applications in repository. Android applications in each group are detected with static analysis and dynamic analysis. We construct a sample set under test after summarizing defect collection.Second, the sample set is taken penetration test by malicious application. Then we extract the effective attacking API sequence from malicious applications. In the end, we obtain the threat trigger model for this category of applications using machine learning.

Copyright

© 2017, 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  - Hao Zengshuai
AU  - Meng Leizi
AU  - Zhan Xiong
AU  - Wang Jie
AU  - Yu Jianbo
PY  - 2017/10
DA  - 2017/10
TI  - A Novel Android Application Penetration Analysis Method
BT  - Proceedings of the 2017 2nd Joint International Information Technology, Mechanical and Electronic Engineering Conference (JIMEC 2017)
PB  - Atlantis Press
SP  - 29
EP  - 35
SN  - 2352-538X
UR  - https://doi.org/10.2991/jimec-17.2017.6
DO  - 10.2991/jimec-17.2017.6
ID  - Zengshuai2017/10
ER  -