DroidDetector: A Traffic-based Platform to Detect Android Malware Using Machine Learning

机译：DroidDetector：基于流量的平台，可使用机器学习检测Android恶意软件

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

With the rapid development of the mobile Intemet,more and more people are using smart phones to access the Internet, especially Android devices, which have become the most popular devices of the moment. Although today's mobile operating systems do their best to provide users with a secure Internet environment, due to the open source nature of Android, it is still unable to completely stop the outbreak of Android malware. Although existing source-based static detection and behavior-based dynamic detection can identify mobile malware, many problems still exist.such as low detection efficiency and difficulty in deployment. In order to solve these problems, we propose DroidDetector, a detection engine that can automatically detect whether an app is a malware or not by using off-line trained machine learning models for network traffic analysis. DroidDetector uses the VPNService class provided by the Android SDK to intercept network traffic (it does not require root permission). All data analysis are performed on the server,which consumes minimun cache and resource on mobile devices. We extract the length of the first 8 packets of network traffic as features and use Support Vector Machine(SVM) classification algorithm to train the model. In an evaluation experiment of 53107 TCP packet length feature tuples samples, DroidDetector can achieve 95. 68% detection confidence.

机译：随着移动互联网的迅猛发展，越来越多的人正在使用智能手机访问Internet，尤其是Android设备，这些设备已成为当前最受欢迎的设备。尽管当今的移动操作系统竭尽所能为用户提供安全的Internet环境，但是由于Android的开源特性，它仍无法完全阻止Android恶意软件的爆发。尽管现有的基于源的静态检测和基于行为的动态检测可以识别移动恶意软件，但仍然存在许多问题，例如检测效率低和部署困难。为了解决这些问题，我们提出了DroidDetector，这是一种检测引擎，可以通过使用脱机训练有素的机器学习模型进行网络流量分析来自动检测应用程序是否为恶意软件。 DroidDetector使用Android SDK提供的VPNService类来拦截网络流量（它不需要root权限）。所有数据分析均在服务器上执行，这会占用最少的缓存和移动设备上的资源。我们提取网络流量的前8个数据包的长度作为特征，并使用支持向量机（SVM）分类算法训练模型。在53107个TCP数据包长度特征元组样本的评估实验中，DroidDetector可以达到95. 68％的检测置信度。

著录项

来源
《Third International Workshop on Pattern Recognition》|2018年|108280N.1-108280N.9|共9页
会议地点 Jinan(CN)
作者
Jingya Shen; Zhenxiang Chen; Shanshan Wang; Yuhui Zhu; Muhammad Umair Hassan;
展开▼
作者单位

School of Information Science and Engineering, University of Jinan,Jinan,China,250022;

School of Information Science and Engineering, University of Jinan,Jinan,China,250022;

School of Information Science and Engineering, University of Jinan,Jinan,China,250022;

School of Information Science and Engineering, University of Jinan,Jinan,China,250022;

School of Information Science and Engineering, University of Jinan,Jinan,China,250022;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Android; Network Traffic; Malware; Machine learning; Detection;

机译：Android；网络流量；恶意软件；机器学习；检测;

相似文献

外文文献
中文文献
专利

1. Droiddetector: android malware characterization and detection using deep learning [J] . Yuan Zhenlong, Lu Yongqiang, Xue Yibo Tsinghua Science and Technology . 2016,第1期

机译：Droiddetector：使用深度学习对Android恶意软件进行表征和检测
2. DroidDetector: Android Malware Characterization and Detection Using Deep Learning [J] . Zhenlong Yuan, Yongqiang Lu, Yibo Xue 清华大学学报（英文版） . 2016,第001期

机译：DroidDetector：使用深度学习的Android恶意软件表征和检测
3. Machine Learning Techniques for Malware Detection on Android Mobile Platform [J] . S. Sivasathya, Kush Manohar International Journal of Applied Engineering Research . 2018,第7aPta1期

机译：用于Android移动平台的恶意软件检测机器学习技术
4. DroidDetector: A Traffic-based Platform to Detect Android Malware Using Machine Learning [C] . Jingya Shen, Zhenxiang Chen, Shanshan Wang, International Workshop on Pattern Recognition . 2018

机译：Droiddetector：使用机器学习检测Android恶意软件的基于流量的平台
5. Android Malware Detection Using Machine Learning Algorithms [D] . Herron, Nathan. 2020

机译：使用机器学习算法进行Android恶意软件检测
6. Detecting and classifying method based on similarity matching of Android malware behavior with profile [O] . Jae-wook Jang, Jaesung Yun, Aziz Mohaisen, -1

机译：基于Android恶意软件行为与配置文件相似度匹配的检测分类方法
7. Droiddetector: android malware characterization and detection using deep learning [O] . Zhenlong Yuan, Yongqiang Lu, Yibo Xue 2016

机译：Droiddetector：使用深度学习的Android恶意软件特征和检测
8. Compilation of a Network Security/Machine Learning Toolchain for Android ARM Platforms. [R] . Ritchey, R. P., Payer, G. S., Harang, R. E. 2014

机译：为android aRm平台编译网络安全/机器学习工具链。

DroidDetector: A Traffic-based Platform to Detect Android Malware Using Machine Learning

摘要

著录项

相似文献

相关主题

期刊订阅