Anomaly Detection Based on Rough Set and BP Neural Network for Android System

摘要

As the Android smart phone becomes more and more popular, its security problems stands out increasingly. According to the advantages and the problems existing in rough sets and neural network, this paper presents a new method which can be used in the Android system anomaly detection. This method simplifies the rough set data based on their attributes, and then use the data as training data to establish a classification model. The experiment results show that: for Android phones, this method has a high recognition rate and detection rate of abnormal behaviors.