Skip to main content
SpringerLink
Log in

Large Margin Multiclass Gaussian Classification with Differential Privacy

  • Conference paper
Privacy and Security Issues in Data Mining and Machine Learning (PSDML 2010)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 6549))

Abstract

As increasing amounts of sensitive personal information is aggregated into data repositories, it has become important to develop mechanisms for processing the data without revealing information about individual data instances. The differential privacy model provides a framework for the development and theoretical analysis of such mechanisms. In this paper, we propose an algorithm for learning a discriminatively trained multiclass Gaussian classifier that satisfies differential privacy using a large margin loss function with a perturbed regularization term. We present a theoretical upper bound on the excess risk of the classifier introduced by the perturbation.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Dwork, C.: Differential privacy. In: Bugliesi, M., Preneel, B., Sassone, V., Wegener, I. (eds.) ICALP 2006. LNCS, vol. 4052, pp. 1–12. Springer, Heidelberg (2006)

    Chapter  Google Scholar 

  2. Chaudhuri, K., Monteleoni, C.: Privacy-preserving logistic regression. In: Neural Information Processing Systems, pp. 289–296 (2008)

    Google Scholar 

  3. McLachlan, G., Peel, D.: Finite Mixture Models. Wiley series in probability and statistics. Wiley-Interscience, Hoboken (2000)

    Book  MATH  Google Scholar 

  4. Sha, F., Saul, L.K.: Large margin gaussian mixture modeling for phonetic classification and recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 265–268 (2006)

    Google Scholar 

  5. Kasiviswanathan, S.P., Lee, H.K., Nissim, K., Raskhodnikova, S., Smith, A.: What can we learn privately? In: IEEE Symposium on Foundations of Computer Science, pp. 531–540 (2008)

    Google Scholar 

  6. Dinur, I., Nissim, K.: Revealing information while preserving privacy. In: Symposium on Principles of Database Systems (2003)

    Google Scholar 

  7. Dwork, C., Nissim, K.: Privacy-preserving datamining on vertically partitioned databases. In: Franklin, M. (ed.) CRYPTO 2004. LNCS, vol. 3152, pp. 528–544. Springer, Heidelberg (2004)

    Chapter  Google Scholar 

  8. Blum, A., Dwork, C., McSherry, F., Nissim, K.: Practical privacy: The suLQ framework. In: Symposium on Principles of Database Systems (2005)

    Google Scholar 

  9. Barak, B., Chaudhuri, K., Dwork, C., Kale, S., McSherry, F., Talwar, K.: Privacy, accuracy, and consistency too: a holistic solution to contingency table release. In: Symposium on Principles of Database Systems, pp. 273–282 (2007)

    Google Scholar 

  10. Dwork, C., McSherry, F., Nissim, K., Smith, A.: Calibrating noise to sensitivity in private data analysis. In: Halevi, S., Rabin, T. (eds.) TCC 2006. LNCS, vol. 3876, pp. 265–284. Springer, Heidelberg (2006)

    Chapter  Google Scholar 

  11. Jagannathan, G., Pillaipakkamnatt, K., Wright, R.N.: A practical differentially private random decision tree classifier. In: ICDM Workshop on Privacy Aspects of Data Mining, pp. 114–121 (2009)

    Google Scholar 

  12. Sha, F., Saul, L.K.: Large margin hidden markov models for automatic speech recognition. In: Neural Information Processing Systems, pp. 1249–1256 (2007)

    Google Scholar 

  13. Mahalanobis, P.C.: On the generalised distance in statistics. Proceedings of the National Institute of Sciences of India 2, 49–55 (1936)

    MATH  Google Scholar 

  14. Chapelle, O.: Training a support vector machine in the primal. Neural Computation 19(5), 1155–1178 (2007)

    Article  MathSciNet  MATH  Google Scholar 

  15. Vandenberghe, L., Boyd, S.: Semidefinite programming. SIAM Review 38, 49–95 (1996)

    Article  MathSciNet  MATH  Google Scholar 

  16. Chaudhuri, K., Monteleoni, C., Sarwate, A.D.: Differentially private empirical risk minimization. arXiv:0912.0071v4 [cs.LG] (2010)

    Google Scholar 

  17. Sridharan, K., Shalev-Shwartz, S., Srebro, N.: Fast rates for regularized objectives. In: Neural Information Processing Systems, pp. 1545–1552 (2008)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Carnegie Mellon University, Pittsburgh, PA, 15213, USA

    Manas A. Pathak & Bhiksha Raj

Authors
  1. Manas A. Pathak
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bhiksha Raj
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Johann Wolfgang Goethe University, Ruth-Moufang-Str. 1, 60438, Frankfurt am Main, Germany

    Christos Dimitrakakis

  2. Information Analytics Lab, IBM Research – Zurich, Säumerstrasse 4, 8803, Rüschlikon, Switzerland

    Aris Gkoulalas-Divanis

  3. Ecole Polytechnice Fédérale de Lausanne, I&C - ISC - LASEC, Bâtiment INF, Station 14, CH-1015, Lausanne, Switzerland

    Aikaterini Mitrokotsa

  4. Department of Computer and Communication Engineering, University of Thessaly, Glavani 37 & 28TH, GR 38221, Octovriou, Volos, Greece

    Vassilios S. Verykios

  5. Faculty of Engineering and Natural Sciences, Sabanci University, Orhanli, 34956, Tuzla, Istanbul, Turkey

    Yücel Saygin

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Pathak, M.A., Raj, B. (2011). Large Margin Multiclass Gaussian Classification with Differential Privacy. In: Dimitrakakis, C., Gkoulalas-Divanis, A., Mitrokotsa, A., Verykios, V.S., Saygin, Y. (eds) Privacy and Security Issues in Data Mining and Machine Learning. PSDML 2010. Lecture Notes in Computer Science(), vol 6549. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19896-0_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-19896-0_9

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-19895-3

  • Online ISBN: 978-3-642-19896-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation