Android Malware Detector Exploiting Convolutional Neural Network and Adaptive Classifier Selection

摘要: Convolutional Neural Network (CNN) has achieved success in Android malware detection and many other fields. However, the empirical evaluation of previous studies have shown that no single machine learning classifier is capable to provide best accuracy any context. In this paper, a new method for proposed, we replace CNN with Adaptive Selection Classifiers (ASC) improve performance classification. We test our on 1746 apk samples 1000 malware, result shows approach performs 4.27% better than state-of–art model used current research.