NNSDS: Network Nodes-Social Attributes Discovery System Based on Netflow

详细信息    查看全文

• 作者：Shuo Mao (20)
  Zhigang Wu (20)
  Bo Sun (21)
  Shoufeng Cao (21)
  Xiongjie Du (21)
  Kaifeng Wang (22)
  
• 关键词：Netflow ; social attributes ; Hadoop ; terminal node
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：8710
• 期：1
• 页码：235-245
• 参考文献：1. Tan, Y., Wu, J., Deng, H.: Evaluation method for node importance based on node contraction in complex networks. Systems Engineering-Theory & Practice?11, 79-3 (2006)
  2. Costa, L.F., Rodrigues, F.A., Travieso, G., et al.: Characterization of complex networks: A survey of measurements. Advances in Physics?56(1), 167-42 (2007) CrossRef
  3. Cisco I O S. Netflow introduction (September 2006), http://www.cisco.com
  4. Estan, C., Varghese, G.: New directions in traffic measurement and accounting. ACM (2002)
  5. Wang, C., Chen, W., Zhang, J.: Challenging Scientific Problems of Technology and Application of Big Data. Bulletin of National Natural Science Foundation of China (2014)
  6. IPFIX. Internet Engineering Task Force, IP Flow Information Export Working Group, http://www.ietf.org/html.charters/ipfix-charter.html
  7. Cisco Sampled Netflow, http://www.cisco.com
  8. Choi, B.Y., Bhattacharyya, S.: On the accuracy and overhead of cisco sampled netflow. In: Proceedings of ACM SIGMETRICS Workshop on Large Scale Network Inference (LSNI) (2005)
  9. Chen, N., Xu, T.: Study on NetFlow-based network traffic data collection and storage. Application Research of Computers?2, 75 (2008)
  10. Li, M., Ye, J., Li, J.: Network Traffic Management Based on Hash Aggregation. Journal of Jiangxi Normal University (Natural Science)?35(3), 174-77 (2011)
  11. Eager, D., Vernon, M., Zahorjan, J.: Optimal and efficient merging schedules for video-on-demand servers. In: Proceedings of the Seventh ACM International Conference on Multimedia (Part 1), pp. 199-02. ACM (1999)
  12. Mokbel, M.F., Lu, M., Aref, W.G.: Hash-merge join: A non-blocking join algorithm for producing fast and early join results. In: Proceedings of the 20th International Conference on Data Engineering, pp. 251-62. IEEE (2004)
  13. Naumann, F., H?ussler, M.: Declarative data merging with conflict resolution (2002)
  14. Lv, Z., Zheng, J., Huang, H.: A Distributed Real-Time Intrusion Detection System for High-Speed Network. Journal of Computer Research and Development?41(4), 667-73 (2004)
  15. Paxson, V., Mahdavi, J., Mathis, M., et al.: Framework for IP performance metrics. Framework (1998)
  16. Wang, J., Zhu, K., Wang, F.: Microblog Fans Network Evolving Model based on User Social Characteristics and Attractiveness of Behavior Properties. Journal of Computer Application?33(10), 2753-756 (2013) CrossRef
  17. Karagiannis, T., Papagiannaki, K., Faloutsos, M.: BLINC: multilevel traffic classification in the dark. In: ACM SIGCOMM Computer Communication Review, vol.?35(4), pp. 229-40. ACM (2005)
  
• 作者单位：Shuo Mao (20)
  Zhigang Wu (20)
  Bo Sun (21)
  Shoufeng Cao (21)
  Xiongjie Du (21)
  Kaifeng Wang (22)
  
  20. Network Information Center, Beijing University of Posts and Telecommunications, 100876, Beijing, China
  21. National Computer Network Emergency Response Technical Team/, Coordination Center of China, 100029, Beijing, China
  22. Beijing TianYuanTeTong Technology Co., Ltd., 100029, Beijing, China
  
• ISSN：1611-3349

文摘

Currently, the most network traffic identification technologies focus on the applications of traffic, while ignoring the attributes of network terminal nodes which generate traffic. In this paper, we present a novel approach to identify the social attributes of network terminal nodes and design Netflow based network Nodes-Social attributes Discovery System(NNSDS).Firstly, we store the Netflow records using two hash tables to obtain the snapshots of the activity of the network. Then we discover the attributes of network nodes by the following elements: (1) social topology statistics, (2) social activity and (3) social roles of network nodes. We test our system on an IP backbone network. The experimental results show that our system can correctly identify various types of network nodes and the identification accuracy achieves 95%.