基于改进朴素贝叶斯的Android恶意应用检测技术

doi:10.13190/j.jbupt.2016.02.009

北京邮电大学学报 ›› 2016, Vol. 39 ›› Issue (2): 43-47.doi: 10.13190/j.jbupt.2016.02.009

基于改进朴素贝叶斯的Android恶意应用检测技术

许艳萍¹, 伍淳华¹, 侯美佳², 郑康锋¹, 姚珊²

1. 北京邮电大学信息安全中心, 北京 100876;
2. 国家计算机网络应急技术处理协调中心, 北京 100029

收稿日期:2015-09-16 出版日期:2016-04-28 发布日期:2016-04-28
作者简介:许艳萍(1986-),女,博士生,E-mail:xyp_xyp@126.com;姚珊(1983-),女,工程师.
基金资助:
国家自然科学基金项目（61272519）；"十二五"国家科技支撑计划项目（2012BAH45B00）

Android Malware Detection Technology Based on Improved Naïve Bayesian

XU Yan-ping¹, WU Chun-hua¹, HOU Mei-jia², ZHENG Kang-feng¹, YAO Shan²

1. Information Security Center, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. National Computer Network Emergency Response Technical Team/Coordination Center of China(CNCERT/CC), Beijing 100029, China

Received:2015-09-16 Online:2016-04-28 Published:2016-04-28

摘要/Abstract

摘要：

在对未知应用静态分析的基础上，提取AndroidManifest.xml中申请的权限为特征，采用信息增益算法优化选择分类特征，再采用拉普拉斯校准、乘数取自然对数改进的朴素贝叶斯算法创建恶意应用分类器.通过十折交叉试验验证改进的朴素贝叶斯分类器的准度和精度较高，且通过信息增益优化选择的分类特征在保障准确率的情况下能有效提高检测效率.与k最近邻和k-Means分类器相比，改进的朴素贝叶斯分类器具有较好的分类效果.

关键词: Android权限, 恶意应用, 信息增益, 朴素贝叶斯

Abstract:

Permissions are extracted as features via static analysis. The information gain (IG) algorithm is applied to select significant features. The Naïve Bayesian (NB) classifier is created which is improved through Laplace calibration and natural logarithm of multiplier. The results with 10-fold cross validation indicate that the improved NB classifier achieves higher accuracy and precision, and the selected features by IG algorithm improve the detection efficiency in ensuring the accuracy of the case. Comparing k-nearest neighbor (KNN) and k-Means classifier, NB classifier has good performance on validity, accuracy and efficiency.

Key words: Android permission, malware application, information gain, Naï, ve Bayesian

中图分类号:

TP309

许艳萍, 伍淳华, 侯美佳, 郑康锋, 姚珊. 基于改进朴素贝叶斯的Android恶意应用检测技术[J]. 北京邮电大学学报, 2016, 39(2): 43-47.

XU Yan-ping, WU Chun-hua, HOU Mei-jia, ZHENG Kang-feng, YAO Shan. Android Malware Detection Technology Based on Improved Naïve Bayesian[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2016, 39(2): 43-47.

[1]	芮兰兰, 张洁, 郭少勇, 熊翱. 基于样本加权的基因特征选取模型[J]. 北京邮电大学学报, 2016, 39(s1): 72-75.
[2]	高联雄, 吴建平. 从智能卡数据挖掘客流信息的算法[J]. 北京邮电大学学报, 2011, 34(3): 94-97.

基于改进朴素贝叶斯的Android恶意应用检测技术

Android Malware Detection Technology Based on Improved Naïve Bayesian

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价