Asymptotically Optimal and Private Statistical Estimation

(Invited Talk)
  • Adam Smith
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5888)


Differential privacy is a definition of “privacy” for statistical databases. The definition is simple, yet it implies strong semantics even in the presence of an adversary with arbitrary auxiliary information about the database.

In this talk, we discuss recent work on measuring the utility of differentially private analyses via the traditional yardsticks of statistical inference. Specifically, we discuss two differentially private estimators that, given i.i.d. samples from a probability distribution, converge to the correct answer at the same rate as the optimal nonprivate estimator.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Blum, A., Dwork, C., McSherry, F., Nissim, K.: Practical Privacy: The SuLQ framework. In: Proceedings of the 24th ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems (June 2005)Google Scholar
  2. 2.
    Blum, A., Ligett, K., Roth, A.: A Learning Theory Approach to Non-Interactive Database Privacy. In: Proceedings of the 40th ACM SIGACT Symposium on Thoery of Computing (2008)Google Scholar
  3. 3.
    Chaudhuri, K., Monteleoni, C.: Privacy-preserving logistic regression. In: Proceedings of the 22nd Annual Conference on Neural Information Processing Systems (NIPS) 2008, pp. 289–296 (2008)Google Scholar
  4. 4.
    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)CrossRefGoogle Scholar
  5. 5.
    Dwork, C.: Differential Privacy: A Survey of Results. In: Agrawal, M., Du, D.-Z., Duan, Z., Li, A. (eds.) TAMC 2008. LNCS, vol. 4978, pp. 1–19. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  6. 6.
    Dwork, C., Lei, J.: Differential Privacy and Robust Statistics. In: Proceedings of the 41st ACM Symposium on Theory of Computing (2009)Google 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., Nissim, K.: Privacy-Preserving Datamining on Vertically Partitioned Databases. In: Franklin, M. (ed.) CRYPTO 2004. LNCS, vol. 3152, pp. 528–544. Springer, Heidelberg (2004)Google Scholar
  9. 9.
    Dwork, C., Smith, A.: Differential Privacy for Statistics: What we Know and What we Want to Learn. In: NCHS/CDC Data Confidentiality Workshop (2008)Google Scholar
  10. 10.
    Kasiviswanathan, S., Lee, H., Nissim, K., Raskhodnikova, S., Smith, S.: What Can We Learn Privately? In: Proc. 49th Annual IEEE Symposium on Foundations of Computer Science (2008)Google Scholar
  11. 11.
    Kasiviswanathan, S., Smith, S.: A Note on Differential Privacy: Defining Resistance to Arbitrary Side Information. Preprint arxiv:0803.3946 (2008),
  12. 12.
    McSherry, F., Talwar, K.: Mechanism Design via Differential Privacy. In: Proceedings of the 48th Annual Symposium on Foundations of Computer Science (2007)Google Scholar
  13. 13.
    McSherry, F., Williams, O.: Probabilistic Inference and Differential Privacy. Manuscript (2009)Google Scholar
  14. 14.
    Nissim, K., Raskhodnikova, S., Smith, A.: Smooth Sensitivity and Sampling in Private Data Analysis. In: Proceedings of the 39th ACM Symposium on Theory of Computing, pp. 75–84 (2007)Google Scholar
  15. 15.
    Smith, A.: Efficient, Differentially Private Point Estimators. Preprint arxiv:0809.4794 (2008),
  16. 16.
    Wasserman, L., Zhou, S.: A statistical framework for differential privacy. Preprint arXiv:0811.2501v1 (2008),

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Adam Smith
    • 1
  1. 1.Pennsylvania State UniversityUniversity ParkUSA

Personalised recommendations