Learning features from enhanced function call graphs for Android malware detection

doi:10.1016/j.neucom.2020.10.054

Learning features from enhanced function call graphs for Android malware detection

2021-01-01

64

PRE

AI

DOI：10.1016/j.neucom.2020.10.054

Original

Original request for help

Save

Abstract

En 中文

Analyzing the runtime behaviors of Android apps is crucial for malware detection. In this paper, we attempt to learn the behavior level features of an app from function calls. The challenges of this task are twofold. First, the absence of function attributes hinders the understanding of app behaviors. Second, the graphical representation of function calls cannot be directly processed by classical machine learning algorithms. In this paper, we develop two methods to overcome these challenges. Based on function embedding, we first propose the concept of enhanced function call graphs (E-FCGs) to characterize app runtime behaviors. We then develop a Graph Convolutional Network (GCN) based algorithm to obtain vector representations of E-FCGs. Extensive experiments show that the features learned by our method can achieve surprisingly high detection performance on a variety of classifiers (e.g., LR, DT, SVM, KNN, RF, MLP and CNN), significantly outperforming the traditional static features. (C) 2020 Elsevier B.V. All rights reserved.

Keywords:

Graph convolutional network

Android malware detection

Function embedding

Function call graph

Learning features from enhanced function call graphs for Android malware detection

Abstract

AI Summary

Journal

Organization