• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Computer-Aided Design, Manufacturing, Modeling and Simulation >MixDroid: A Multi-features and Multi-classifiers Bagging System for Android Malware Detection
【24h】

MixDroid: A Multi-features and Multi-classifiers Bagging System for Android Malware Detection

机译：Mixdroid：用于Android Malware检测的多种功能和多分类器堆垛系统

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In the past decade, Android platform has rapidly taken over the mobile market for its superior convenience and open source characteristics. However, with the popularity of Android, malwares targeting on Android devices are increasing rapidly, while the conventional rule-based and expert-experienced approaches are no longer able to handle such explosive growth. In this paper, combining with the theory of natural language processing and machine learning, we not only implement the basic feature extraction of permission application features, but also propose two innovative schemes of feature extraction: Dalvik opcode features and malicious code image, and implement an automatic Android malware detection system MixDroid which is based on multi-features and multi-classifiers. According to our experiment results on 20,000 Android applications, detection accuracy of MixDroid is 98.1%, which proves our schemes' effectiveness in Android malware detection.
机译：在过去十年中，Android平台迅速接管了移动市场，以获得其优异的便利性和开源特征。然而，随着Android的普及，针对Android设备的恶意速度正在迅速增加，而传统的基于规则和专家经验丰富的方法不再能够处理这种爆炸性的增长。在本文中，与自然语言处理和机器学习理论相结合，我们不仅实现了许可应用功能的基本特征提取，还提出了两种特征提取方案：Dalvik Opcode功能和恶意代码图像，并实现了一个自动Android恶意软件检测系统Mixdroid，其基于多功能和多分类器。根据我们的实验结果，Mixdroid的检测精度为98.1％，这证明了我们的方案在Android恶意软件检测中的有效性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号