基于Android恶意软件检测技术的研究

Detection Technology Research of Malware Based on Android

近年来,随着Android智能终端的普及,人们在享受其所带来的便利的同时,也越来越多的受到各类恶意软件的攻击。因此,为了减小用户遭受威胁的可能性,论文就恶意吸费、隐私窃取及资费消耗这三类软件进行研究,提出一种基于混合特征的Android恶意软件检测方法,结合动态检测方法和静态检测方法,构造出一种混合特征集,然后选用多种分类算法对该混合特征集进行分类,根据比较结果,选定一种最优的分类方法,提高用户使用软件的安全性。通过实验仿真,结果表明该方法在恶意软件检测中应用效果良好。

In recent years,with the popularity of Android intelligent terminal,people enjoy the convenience brought by it.But at the same time,more and more intelligent terminals attack by various types of malicious software.Therefore,in order to reduce the possibility of the user being threatened,this subject focuses on three kinds of software,malicious charges,privacy stealing and consumption.This paper proposes a detection method of Android malware based on mixed features.This method combines dynamic detection method and static detection method to construct a mixed feature set.And then use a variety of classification algorithms for classification of the mixed feature set.According to the comparison result,an optimal classification method is selected to improve the security of the software.The simulation results show that the proposed method is effective in malware detection.