Advertisement

Consensus-Based Privacy-Preserving Algorithm

  • Heng Li
  • Fangfang Xu
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 463)

Abstract

In this paper, we use secure multi-party computation to protect privacy. Based on consensus-based distributed support vector machines, we present a new consensus-based privacy-preserving algorithm to conduct secure multi-party computation. The proposed algorithm run in parallel at each iteration, which reduce the running time. Furthermore, what needed to be communicated at each iteration is only a coefficient vector, therefore privacy is protected to the uttermost. The algorithm is proved to be convergent globally. Numerical experiments demonstrate the feasibility and efficiency of the new algorithm.

Keywords

Secure multi-party computation Privacy preserving Support vector machine Parallel computation Global convergence 

References

  1. 1.
    Lu, Y., Roychowdhury, V., Vandenberghe, L.: Distributed parallel support vector machines in strongly connected networks. IEEE Trans. Neural Netw. 19, 1167–1178 (2008)Google Scholar
  2. 2.
    Navia-Vazquez, A., Gutierrez-Gonzalez, D., Parrado-Hernandez, E., Navarro-Abellan, J.J.: Distributed support vector machines. IEEE Trans. Neural Netw. 17, 1091–1097 (2006)Google Scholar
  3. 3.
    Forero, P.A., Cano, A., Giannakis, G.B.: Consensus-based distributed support vector machines. J. Mach. Learn. Res. 11, 1663–1707 (2010)Google Scholar
  4. 4.
    Lindell, Y., Pinkas, B.: Secure multiparty computation for privacy-preserving data mining. J. Privacy Confidentiality 1, 59–98 (2009)Google Scholar
  5. 5.
    Zhang, Y., Zhong, S.: A privacy-preserving algorithm for distributed training of neural network ensembles. Neural Comput. Appl. 22, 269–282 (2013)Google Scholar
  6. 6.
    Wang, L., Shi, J.J., Chen, C., Zhong, S.: Privacy-preserving face detection based on linear and nonlinear kernels. In: Multimedia Tools and Applications, pp. 1–21 (2017)Google Scholar
  7. 7.
    Forero, P.A., Cano, A., Giannakis, G.B.: Consensus-based K-means algorithm for distributed learning using wireless sensor networks. In: Proceedings of Workshop on Sensors, Signal and Information Processing, Sedona, AZ, May 2008Google Scholar
  8. 8.
    Bertsekas, D.P., Tsitsiklis, J.N.: Parallel and Distributed Computation: Numerical Methods. Athena Scientific, Massachusetts (1997)Google Scholar
  9. 9.
    Asuncion, A., Newman, D.J.: Statlog training set. http://www.csie.ntu.edu.tw/cjlin/libsvmtools/datasets/
  10. 10.
    Flouri, K., Beferull-Lozano, P., Tsakalides, P.: Training a support-vector machine-based classifier in distributed sensor networks. In: Proceedings of 14th European Signal Processing Conference, Florence, Italy, 4–8 September 2006Google Scholar
  11. 11.
    Flouri, K., Beferull-Lozano, P., Tsakalides, P.: Distributed consensus algorithm for SVM training in wireless sensor networks. In: Proceedings of 16th European Signal Processing Conference, Laussane, Switzerland, 25–29 August 2008Google Scholar
  12. 12.
    Bennati, S., Jonker, C.M.: PriMaL: a privacy-preserving machine learning method for event detection in distributed sensor networks (2017)Google Scholar
  13. 13.
    Mangasarian, O.L., Wild, E.W., Fung, G.M.: Privacy-preserving classification of horizontally partitioned data via random kernels. In: Proceedings of the 2008 International Conference on Data Mining, vol. 2, pp. 473–479 (2008)Google Scholar
  14. 14.
    Ruan, M., Wang, Y.: Secure and privacy-preserving average consensus (2017)Google Scholar
  15. 15.
    Sagastizabal, C.A., Solodov, M.V.: Parallel variable distribution for constrained optimization. Comput. Optim. Appl. 22, 111–131 (2002)Google Scholar
  16. 16.
    Ceccarello, M., Pietracaprina, A., Pucci, G., et al.: A practical parallel algorithm for diameter approximation of massive weighted graphs. In: IEEE International Parallel and Distributed Processing Symposium, pp. 12–21 (2016)Google Scholar
  17. 17.
    Do, T.N., Nguyen, V.H., Poulet, F.: GPU-based parallel SVM algorithm. J. Front. Comput. Sci. Technol. 3, 368–377 (2009)Google Scholar
  18. 18.
    Dai, Y.H., Fletcher, R.: New algorithms for singly linearly constrained quadratic programs subject to lower and upper bounds. Math. Program. 20, 403–421 (2006)Google Scholar
  19. 19.
    Solodov, M.V.: New inexact parallel variable distributed algorithm. Comput. Optim. Appl. 7, 165–182 (1997)Google Scholar
  20. 20.
    Zanni, L.: An improved gradient projection-based decomposition technique for support vector machines. CMS 3, 131–145 (2006)Google Scholar
  21. 21.
    Huang, M., Chen, Y., Chen, B.W., et al.: A semi-supervised privacy-preserving clustering algorithm for healthcare. Peer-to-Peer Netw. Appl. 9, 864–875 (2016)Google Scholar
  22. 22.
    Canetti, R.: Security and composition of multi-party cryptographic protocols. J. Cryptology 13, 143–202 (2000)Google Scholar
  23. 23.
    Zhang, M.L., Han, M., Wang, Z.Z.: Inter-systems privacy-preserving recommendation algorithm based on security multi-party computation. J. Hebei Univ. Technol. (2012)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.College of Foreign LanguagesShandong University of Science and TechnologyQingdaoPeople’s Republic of China
  2. 2.College of Mathematics and Systems ScienceShandong University of Science and TechnologyQingdaoPeople’s Republic of China

Personalised recommendations