基于BPSO-NB算法的Android恶意应用检测方法

为了提高Android恶意应用检测效率，将二值粒子群算法(BPSO，Binary Particle Swarm Optimization)用于原始特征全集的优化选择，并结合朴素贝叶斯(NB，Nave Bayesian)分类算法，提出一种基于BPSO-NB的Android恶意应用检测方法。该方法首先对未知应用进行静态分析，提取AndroidManifest.xml文件中的权限信息作为特征。然后，采用BPSO算法优化选择分类特征，并使用NB算法的分类精度作为评价函数。最后采用NB分类算法构建Android恶意应用分类器。实验结果表明，通过二值粒子群优化选择分类特征可以有效提高分类精度，缩短检测时间。 

Android Malware Application Detection Method Based on BPSO-NB

 In order to improve the efficiency of Android malware application detection, the binary particle swarm optimization (BPSO) is used for optimal selection of complete ensemble of original features, combined with the Nave Bayesian (NB) classification algorithm，an Android malware detection method based on BPSO-NB algorithm is proposed. First, this method uses static analysis for unknown applications to extract the permission information in an AndroidManifest.XML file as a feature. Then, it uses the BPSO algorithm to optimize selected classification feature,  and uses the classification accuracy of  NB algorithm as the evaluation function. Finally, NB classification algorithm is used to construct classifier for Android malicious applications. Through cross experiment, BPSO-NB classification equipment has higher classification accuracy, and the optimal selection of BPSO algorithm classification characteristics under the condition of the security classification accuracy can effectively improve the efficiency of detection.