Android malware detection method based on byte-code image and deep learning

Abstract

A new Android malware detection method based on byte-code image and deep learning was proposed. Firstly, Android malware byte-code files were mapped to RGB colorful images which had three channels. Also, the Shannon entropy as Alpha channel of images were calculated, and then merged with RGB images into RGBA images. Finally, the convolutional neural network as classifier was employed to classify aforementioned images. According to the experiment on malware of eight malicious families and compared this method with the method which mapping the byte-code to gray image, the result shows that the method using RGBA images has good performance not only in speed, but also in accuracy.

Keywords

• malware detection;byte-code image;Shannon entropy;deep learning;classification