An Android malware detection Approach based on Weisfeiler-Lehman Kernel

DOI

10.2991/cnci-19.2019.75How to use a DOI?

Keywords

Malware, graph kernel, call graph, context.

Abstract

The explosive growth of Android malware has caused great harm to users' lives and work. In this work, we propose an Android malware detection approach based on Weisfeiler-Lehman (WL) kernel, which converts malware detection problem into similarity analysis problem of function call graph, and introduce contextual information of function call process to enhance nodes label of function call graph. The node label enables the feature space to contain both the structural information and the contextual information of the graph. The similarity of the function call graph is calculated by the Weisfeiler-Lehman graph kernel algorithm to detect the Android malware. Our experimental results show that the WL kernel method enhanced by contextual information is higher than three state-of-the-art kernel methods of CWLK, NHGK and WLK and two classical detection methods of Drebin and Androguard in precision and recall rate.

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  - Fangye Chen
PY  - 2019/05
DA  - 2019/05
TI  - An Android malware detection Approach based on Weisfeiler-Lehman Kernel
BT  - Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019)
PB  - Atlantis Press
SP  - 538
EP  - 545
SN  - 2352-538X
UR  - https://doi.org/10.2991/cnci-19.2019.75
DO  - 10.2991/cnci-19.2019.75
ID  - Ling2019/05
ER  -