Deep Neural Network Based on Android Mobile Malware Detection System Using Opcode Sequences

Malware detection is more challenging due to the increase in android malicious programs and the current problems of android malicious detection. This paper proposes an android mobile malware detection system based on deep neural network, a novel malware detection method which uses optimized deep Convolutional Neural Network to learn from opcode sequences. In the proposed detection system, the optimized Convolutional Neural Network is trained multiple times by the raw operation code sequence extracted from the decompiled android file, so that the feature information can be effectively learned and the malicious program can be detected more accurately. More critically, the k-max pooling method with better results was adopted in the pooling operation phase, and which improves the detection effect of the proposed method. The experimental results show that the detection system achieved the accuracy of 99%, which is 2%-11 % higher than the accuracy of the machine learning detection algorithms when using the same dataset. It also ensures that the indicators such as Fl-score, Recall and Precision are maintained above 97%.