Recently, deep learning has been widely applying to speech and image recognition. Convolutional neural network (CNN) is one of the main categories to do images classifications with a very high accuracy. In Android malware classification field, to take advantages of the CNN model, many works have been trying to convert Android malwares into “images” to make them well-matched with the CNN input. The performance, however, is not significant improved because simply converting malwares into images may lack several important features of the malwares. This paper proposes a method for improving the feature set of Android malware classification based on co-concurrence matrix (co-matrix). The co-matrix is established based on a list of raw features extracted from .APK files. The proposed feature can take the advantage of CNN while remaining important features of the Android malwares. Experimental results of CNN model conducted on a very popular Android malware dataset, Drebin, proves the feasibility of our proposed co-matrix feature.
