关键词: Android应用, 检测方法, Opcode操作码, 特征选择, 卷积神经网络

Abstract: With the accelerating popularity of Android smart devices and the continuous development of the Android application market, security threats have begun to appear. How to detect malicious applications on the Android platform has become an important security issue to be solved. The detection of Android malicious applications has gradually become a research hotspot. The paper summarizes the related work and proposes an Android malware detection method based on convolutional neural network. The method uses the Opcode as research object to describe the Android application more comprehensively. Whats more, the method simplifies artificial feature selection and applies convolutional neural network to automatically extract features from large amounts of samples. Experimental results show that the method can effectively detect malicious applications and provide an effective direction for future research.

Key words: Android application, detection method, Opcode, feature selection, convolutional neural network