信息网络安全 ›› 2016, Vol. 16 ›› Issue (8): 39-45.doi: 10.3969/j.issn.1671-1122.2016.08.007

• • 上一篇    下一篇

基于流量分析的手机应用识别系统的设计与实现

林建军1,2(), 林柏钢2,3, 杨旸2,3, 孙波1   

  1. 1.中国科学院信息工程研究所,北京 100093
    2.福州大学数学与计算机科学学院,福建福州 350108
    3.网络系统信息安全福建省高校重点实验室,福建福州 350108
  • 收稿日期:2016-06-29 出版日期:2016-08-20 发布日期:2020-05-13
  • 作者简介:

    作者简介: 林建军(1994—),男,福建,博士研究生,主要研究方向为信息安全;林柏钢(1953—),男,福建,教授,主要研究方向为网络与信息安全、编码与密码;杨旸(1984—),女,湖北,讲师,博士,主要研究方向为密码学与信息安全;孙波(1972—),男,吉林,高级工程师,博士,主要研究方向为网络安全。

  • 基金资助:
    国家自然科学基金[61402112]

Design and Implementation of Mobile Phone Application Recognition System Based on Traffic Analysis

Jianjun LIN1,2(), Bogang LIN2,3, Yang YANG2,3, Bo SUN1   

  1. 1. Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China
    2.College of Mathematics and Computer Science, Fuzhou University, Fuzhou Fujian 350108, China
    3. Key Lab of Information Security of Network System in Fujian Province, Fuzhou Fujian 350108, China
  • Received:2016-06-29 Online:2016-08-20 Published:2020-05-13

摘要:

随着移动互联网的快速发展,手机中存储了大量的有用信息。如何从中挖掘出有价值的信息,这是人们十分关注的问题。通过分析手机产生的流量来识别手机上安装的应用可以作为手机信息挖掘的初步工作。文章设计了一个基于Django框架的系统,用于从手机流量中提取出手机应用信息。通过分析主流的流量识别技术和模式匹配算法,从中选取合适的技术和算法用于系统设计。文章将系统分为流量分析、特征库、数据库和前端4个模块,并对每个模块的实现进行了详细说明。最后选取了44款手机应用对系统进行了测试,结果显示了较高的识别率。

关键词: 手机应用识别, 深度包检测技术, 流量分析, AC算法

Abstract:

With the rapid development of mobile Internet, Mobile phones store a great deal of useful information. How to dig out valuable information according to actual needs is a problem that people pay close attention to. Identifying the applications installed on a mobile phone by analyzing the traffic generated by the mobile phone can be a preliminary work of mobile phone information mining. This paper designed a system based on Django to extract information of mobile phone applications from mobile phone traffic. By reading relevant material and literature, we investigated the mainstream traffic identification technology and pattern matching algorithms and selected proper technology and algorithms from them to apply to the design of the system. We divided the system into 4 modules: traffic analysis module, feature library module, database module and front end module, and explicated the realization of every module. Finally, we selected 44 mobile phone applications to test the system. It turned out that the recognition rate was high.

Key words: mobile phone application identification, deep packet inspection, traffic analysis, AC algorithm

中图分类号: