Encrypted social media traffic classification

加密社交媒体流量分类

• 批准号: 522181-2017
• 负责人: Mohammadi, Farah
• 金额: $ 1.82万
• 依托单位: Ryerson University
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=640072
• 关键词: Encrypted; social; media; traffic; classification

Network traffic packets carry data belonging to a variety of applications. Classification of traffic helps networkoperators to identify specific applications and protocols that exist in a network, which can be useful for manydifferent purposes such as network planning, application prioritization for QoS guarantees, and policydeployment for security control.Network traffic monitoring is becoming a necessity in network security. The packets of social media suchas Facebook, Twitter, WhatsApp, Snapchat, Instagram, Weibo and WeChat are encrypted. Therefore, analyzingand classification is a challenge. The social networks cover various types of data such as video, text, picturewhich should be considered in classification. Encryption protocols such as Internet Protocol Security (IPsec),TLS, SSH, Bit Torrent, and Skype protocols was also influenced by protocols that are the most commonly usedin research of encrypted traffic classification. Almost all the presented encryption protocols can be divided intotwo main phases: the initialization of the connection and the transport of encrypted data.The objective of this project is to develop machine learning algorithms for classification of social media inencrypted traffic.This project will pull together talents from Ryerson University and Solana Networks and take theadvantage of the resources of Ryerson including experienced researchers, energetic and goal-driven graduatestudents with a track record of excellence of Solana Networks in design and development of the machinelearning based classifier to jointly advance encrypted social media traffic classification and analysis.

网络业务分组携带属于各种应用的数据。流量分类有助于网络运营商识别网络中存在的特定应用和协议，这可以用于许多不同的目的，如网络规划，QoS保证的应用优先级，以及安全控制的策略部署。Facebook、Twitter、WhatsApp、Snapchat、Instagram、微博和微信等社交媒体的数据包都是加密的。因此，分析和分类是一个挑战。社交网络涵盖了视频、文本、图片等各种类型的数据，在分类时应予以考虑。加密协议，如Internet Protocol Security（IPSec）、TLS、SSH、Bit Torrent和Skype协议，也受到加密流量分类研究中最常用的协议的影响。几乎所有的加密协议都可以分为两个主要阶段：连接的初始化和加密数据的传输。该项目的目标是开发用于加密流量中社交媒体分类的机器学习算法。该项目将汇集瑞尔森大学和Solana Networks的人才，并利用瑞尔森的资源，包括经验丰富的研究人员，充满活力和目标驱动的研究生，在设计和开发基于机器学习的分类器方面拥有索拉纳网络的卓越记录，共同推进加密社交媒体流量分类和分析。