摘要:流量混淆技术是目前审查规避系统常用技术之一.为了提升网络流量识别精度和监管能力，针对混淆流量的识别和追踪技术也备受关注.通过深入分析随机化、拟态和隧道这3类主流的流量混淆技术，对比了其技术框架、隐蔽性、易用性和应用场景；分析了深度包检测、机器学习等两类识别技术，对比了其识别精度；分析对比了被动关联、主动关联两类流量追踪技术.最后给出了流量混淆、识别和追踪技术的发展趋势.



Abstract:Traffic obfuscation technology is one of the most commonly used techniques in censorship-circumvention systems. In order to improve the recognition accuracy and supervisory ability of network traffic, much attention has been paid to the recognition and tracking of obfuscated traffic. Through in-depth analysis of three main traffic confusion technologies, such as randomization, mimicry and tunneling, this paper compares the technical framework, concealment, ease of use and application scenarios of the traffic confusion technologies. In addition, the paper reviews two types of recognition technology:deep packet inspection and machine learning, and compares their recognition accuracy. Furthermore, it analyzes and compares two types of traffic tracing technology:passive and proactive correlation. Finally, it discusses the identification and trace technology development trends of obfuscation traffic.



PDF全文下载地址:

http://jos.org.cn/jos/article/pdf/5620