Private-Preserving Analysis of Network Traffic

  • Yang Tang
  • Yan MaEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 550)


Network traffic analysis has important applications in many fields, such as the quality of service provisioning, network monitoring, network optimization, and so on. We can get regional network situation by analyze all parties’ data, however, the cooperation among multiple parties suffers an extra drag from privacy and regulation issues. In this work, we apply secure multi-party computation methods to analyze more than three parties’ traffic data without revealing the secrets themselves. We present a clustering method based on IP network prefix and apply it to the traffic. Through the results of clustering, we can get subnets with the most considerable traffic in the network, and make relevant network settings for these subnets.


Secure multi-party computation Netstream Unsupervised machine learning Clustering 



The work in this paper is supported by the Joint Funds of National Natural Science Foundation of China and Xinjiang (Project U1603261).


  1. 1.
    Snort. Accessed 19 Oct 2018
  2. 2.
    Shafiq, M., Yu, X., Laghari, A.A., Yao, L., Karn, N.K., Abdessamia, F.: Network traffic classification techniques and comparative analysis using machine learning algorithms. In: 2016 2nd IEEE International Conference on Computer and Communications (ICCC), pp. 2451–2455. IEEE (2016)Google Scholar
  3. 3.
    Shadi, K., Natarajan, P., Dovrolis, C.: Hierarchical ip flow clustering. ACM SIGCOMM Comput. Commun. Rev. 47(5), 48–53 (2017)CrossRefGoogle Scholar
  4. 4.
    Erman, J., Arlitt, M., Mahanti, A.: Traffic classification using clustering algorithms. In: Proceedings of the 2006 SIGCOMM Workshop on Mining Network Data, pp. 281–286. ACM (2006)Google Scholar
  5. 5.
    Lindell, Y.: Secure multiparty computation for privacy preserving data mining. In: Encyclopedia of Data Warehousing and Mining, pp. 1005–1009. IGI Global (2005)Google Scholar
  6. 6.
  7. 7.
    Rokach, L., Maimon, O.: Clustering methods. In: Data Mining and Knowledge Discovery Handbook, pp. 321–352. Springer (2005)Google Scholar
  8. 8.
    Clifton, C., Kantarcioglu, M., Vaidya, J., Lin, X., Zhu, M.Y.: Tools for privacy preserving distributed data mining. ACM SIGKDD Explor. Newsl. 4(2), 28–34 (2002)CrossRefGoogle Scholar
  9. 9.
    Ly, J.T.: A serial version of the pohlig-hellman algorithm for computing discret logarithms. Appl. Algebra Eng. Commun. Comput. 4(1), 77–80 (1993)CrossRefGoogle Scholar
  10. 10.
    Beaver, D.: Efficient multiparty protocols using circuit randomization. In: Annual International Cryptology Conference, pp. 420–432. Springer (1991)Google Scholar
  11. 11.
    Koga, H.: A simple secret sharing scheme using a key and its security against substitution of shares. In: 2010 IEEE International Symposium on Information Theory Proceedings (ISIT), pp. 2483–2487. IEEE (2010)Google Scholar
  12. 12.
    Shamir, A.: How to share a secret. Commun. ACM 22(11), 612–613 (1979)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Network Information CenterBeijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations