Advertisement

Abstract

In this paper, we focus on the problem of private database release in the interactive setting: a trusted database curator receives queries in an online manner for which it needs to respond with accurate but privacy preserving answers. To this end, we generalize the IDC (Iterative Database Construction) framework of [15,13] that maintains a differentially private artificial dataset and answers incoming linear queries using the artificial dataset. In particular, we formulate a generic IDC framework based on the Mirror Descent algorithm, a popular convex optimization algorithm [1]. We then present two concrete applications, namely, cut queries over a bipartite graph and linear queries over low-rank matrices, and provide significantly tighter error bounds than the ones by [15,13].

Keywords

Potential Function Bipartite Graph Failure Probability Interactive Setting Privacy Guarantee 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Beck, A., Teboulle, M.: Mirror descent and nonlinear projected subgradient methods for convex optimization. Oper. Res. Lett. 31(3), 167–175 (2003)MathSciNetzbMATHCrossRefGoogle Scholar
  2. 2.
    Blum, A., Ligett, K., Roth, A.: A learning theory approach to non-interactive database privacy. In: STOC (2008)Google Scholar
  3. 3.
    Candes, E.J., Tao, T.: Near-optimal signal recovery from random projections: universal encoding strategies? IEEE Transactions on Information Theory (2006)Google Scholar
  4. 4.
    Dinur, I., Dwork, C., Nissim, K.: Revealing information while preserving privacy, full version of [5] (2010) (in preparation)Google Scholar
  5. 5.
    Dinur, I., Nissim, K.: Revealing information while preserving privacy. In: PODS, pp. 202–210. ACM (2003)Google Scholar
  6. 6.
    Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., Naor, M.: Our Data, Ourselves: Privacy Via Distributed Noise Generation. In: Vaudenay, S. (ed.) EUROCRYPT 2006. LNCS, vol. 4004, pp. 486–503. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  7. 7.
    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)CrossRefGoogle Scholar
  8. 8.
    Dwork, C., McSherry, F., Talwar, K.: The price of privacy and the limits of LP decoding. In: STOC, pp. 85–94. ACM (2007)Google Scholar
  9. 9.
    Dwork, C., Rothblum, G.N., Vadhan, S.P.: Boosting and differential privacy. In: FOCS (2010)Google Scholar
  10. 10.
    Frieze, A.M., Kannan, R.: A simple algorithm for constructing szemere’di’s regularity partition. Electr. J. Comb. (1999)Google Scholar
  11. 11.
    Ganta, S.R., Kasiviswanathan, S.P., Smith, A.: Composition attacks and auxiliary information in data privacy. In: KDD 2008: Proceeding of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 265–273. ACM (2008)Google Scholar
  12. 12.
    Gupta, A., Hardt, M., Roth, A., Ullman, J.: Privately releasing conjunctions and the statistical query barrier. In: STOC (2011)Google Scholar
  13. 13.
    Gupta, A., Roth, A., Ullman, J.: Iterative constructions and private data release. CoRR, abs/1107.3731 (2011)Google Scholar
  14. 14.
    Hardt, M., Ligett, K., McSherry, F.: A simple and practical algorithm for differentially private data release. CoRR, abs/1012.4763 (2010)Google Scholar
  15. 15.
    Hardt, M., Rothblum, G.N.: A multiplicative weights mechanism for privacy-preserving data analysis. In: FOCS (2010)Google Scholar
  16. 16.
    Jain, P., Thakurta, A.: Mirror descent based database privacy. Technical Report NAS-TR-0159-2012, Pennsylvania State University (April 2012)Google Scholar
  17. 17.
    Kakade, S.M., Shalev-Shwartz, S., Tewari, A.: On the duality of strong convexity and strong smoothness: Learning applications and matrix regularization. Informal Publication (2009)Google Scholar
  18. 18.
    Kasiviswanathan, S.P., Lee, H.K., Nissim, K., Raskhodnikova, S., Smith, A.: What can we learn privately? In: FOCS (2008)Google Scholar
  19. 19.
    Roth, A., Roughgarden, T.: Interactive privacy via the median mechanism. In: STOC (2010)Google Scholar
  20. 20.
    Srebro, N., Sridharan, K., Tewari, A.: On the universality of online mirror descent. CoRR, abs/1107.4080 (2011)Google Scholar
  21. 21.
    Vershynin, R.: Introduction to the non-asymptotic analysis of random matrices. CoRR, abs/1011.3027 (2010)Google Scholar
  22. 22.
    Yuan, M., Lin, Y.: Model selection and estimation in regression with grouped variables. Journal of the Royal Statistical Society, Series B 68, 49–67 (2007)MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Prateek Jain
    • 1
  • Abhradeep Thakurta
    • 2
  1. 1.Microsoft ResearchIndia
  2. 2.Pennsylvania State UniversityUSA

Personalised recommendations