Research of Android Malware Detection based on ACO Optimized Xgboost Parameters Approach

DOI

10.2991/icmeit-19.2019.60How to use a DOI?

Keywords

ACO, Xgboost, Android, malware, detection classification.

Abstract

In order to deal with low efficiency and accuracy of detection caused by the improper selection of Xgboost parameters in Android malware detection. In this paper, we introduce Ant Colony Optimization (ACO) into Xgboost parameters optimization and propose an approach based on ACO optimize Xgboost parameters in Android malware detection. Selecting features such as permissions, intents and APIs in AndroidManifest.xml and smali files and extra the optimal feature subset, then apply to the proposed method. The experimental results show that the proposed method effectively improves accuracy of detection and reduces false positive rate compared with the Xgboost algorithm optimized by Genetic Algorithm (GA) and Particle Swarm Optimization (PSO).

Copyright

© 2019, 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  - Jie Ling
AU  - Xuejing Wang
AU  - Yu Sun
PY  - 2019/04
DA  - 2019/04
TI  - Research of Android Malware Detection based on ACO Optimized Xgboost Parameters Approach
BT  - Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)
PB  - Atlantis Press
SP  - 364
EP  - 371
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmeit-19.2019.60
DO  - 10.2991/icmeit-19.2019.60
ID  - Ling2019/04
ER  -