Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9985)

Abstract

“Concentrated differential privacy” was recently introduced by Dwork and Rothblum as a relaxation of differential privacy, which permits sharper analyses of many privacy-preserving computations. We present an alternative formulation of the concept of concentrated differential privacy in terms of the Rényi divergence between the distributions obtained by running an algorithm on neighboring inputs. With this reformulation in hand, we prove sharper quantitative results, establish lower bounds, and raise a few new questions. We also unify this approach with approximate differential privacy by giving an appropriate definition of “approximate concentrated differential privacy”.

References

  1. [BLR13]
    Blum, A., Ligett, K., Roth, A.: A learning theory approach to noninteractive database privacy. J. ACM 60(2), 12 (2013)MathSciNetCrossRefMATHGoogle Scholar
  2. [BNS13]
    Beimel, A., Nissim, K., Stemmer, U.: Private learning and sanitization: pure vs. approximate differential privacy. In: Raghavendra, P., Raskhodnikova, S., Jansen, K., Rolim, J.D.P. (eds.) APPROX/RANDOM -2013. LNCS, vol. 8096, pp. 363–378. Springer, Heidelberg (2013). doi:10.1007/978-3-642-40328-6_26 CrossRefGoogle Scholar
  3. [BNS16]
    Bun, M., Nissim, K., Stemmer, U.: Simultaneous private learning of multiple concepts. In: Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science, ITCS 2016, pp. 369–380. ACM, New York (2016)Google Scholar
  4. [BUV14]
    Bun, M., Ullman, J., Vadhan, S.P.: Fingerprinting codes and the price of approximate differential privacy. In: Symposium on Theory of Computing, STOC 2014, New York, NY, USA, 31 May - 03 June 2014, pp. 1–10 (2014)Google Scholar
  5. [De12]
    De, A.: Lower bounds in differential privacy. In: Cramer, R. (ed.) TCC 2012. LNCS, vol. 7194, pp. 321–338. Springer, Heidelberg (2012). doi:10.1007/978-3-642-28914-9_18 CrossRefGoogle Scholar
  6. [DKM+06]
    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). doi:10.1007/11761679_29 CrossRefGoogle Scholar
  7. [DL09]
    Dwork, C., Lei, J.: Differential privacy and robust statistics. In: Proceedings of the 41st Annual ACM Symposium on Theory of Computing, STOC 2009, Bethesda, MD, USA, 31 May - 2 June 2009, pp. 371–380 (2009)Google Scholar
  8. [DMNS06]
    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). doi:10.1007/11681878_14 CrossRefGoogle Scholar
  9. [DR16]
    Dwork, C., Rothblum, C.: Concentrated differential privacy. CoRR, abs/1603.01887 (2016)Google Scholar
  10. [DRV10]
    Dwork, C., Rothblum, G.N., Vadhan, S.P.: Boosting and differential privacy. In: IEEE Symposium on Foundations of Computer Science (FOCS 2010), pp. 51–60. IEEE, 23–26 October 2010Google Scholar
  11. [HT10]
    Hardt, M., Talwar, K.: On the geometry of differential privacy. In: Proceedings of the Forty-Second ACM Symposium on Theory of Computing, STOC 2010, pp. 705–714, New York, NY, USA. ACM (2010)Google Scholar
  12. [KOV15]
    Kairouz, P., Oh, S., Viswanath, P.: The composition theorem for differential privacy. In: Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, pp. 1376–1385, 6–11 July 2015Google Scholar
  13. [MMP+10]
    McGregor, A., Mironov, I., Pitassi, T., Reingold, O., Talwar, K., Vadhan, S.P.: The limits of two-party differential privacy. In: 51th Annual IEEE Symposium on Foundations of Computer Science, FOCS 23–26, 2010, Las Vegas, Nevada, USA, pp. 81–90, October 2010Google Scholar
  14. [MT07]
    McSherry, F., Talwar, K.: Mechanism design via differential privacy. In: 48th Annual IEEE Symposium on Foundations of Computer Science, FOCS 2007, pp. 94–103, October 2007Google Scholar
  15. [MV16]
    Murtagh, J., Vadhan, S.P.: The complexity of computing the optimal composition of differential privacy. In: Proceedings of Theory of Cryptography - 13th International Conference, TCC2016-A, Tel Aviv, Israel, 10-13 January 2016, Part I, pp. 157–175 (2016)Google Scholar
  16. [Ren61]
    Rényi, A.: On measures of entropy, information. In: Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics, Probability: Contributions to the Theory of Statistics, vol. 1, pp. 547–561. University of California Press (1961)Google Scholar
  17. [SU15a]
    Steinke, T., Ullman, J.: Between pure and approximate differential privacy. CoRR, abs/1501.06095 (2015)Google Scholar
  18. [SU15b]
    Steinke, T., Ullman, J.: Interactive fingerprinting codes, the hardness of preventing false discovery. In: COLT (2015). http://arXiv.org/abs/1410.1228
  19. [Tar08]
    Tardos, G.: Optimal probabilistic fingerprint codes. J. ACM 55(2), 10 (2008)MathSciNetCrossRefMATHGoogle Scholar
  20. [Ull13]
    Ullman, J.: Answering n \(\{\)2+ o (1)\(\}\) counting queries with differential privacy is hard. In: Proceedings of the Forty-Fifth Annual ACM Symposium on Theory of Computing, pp. 361–370. ACM (2013)Google Scholar
  21. [vEH14]
    van Erven, T., Harremos, P.: Rényi divergence and kullback-leibler divergence. IEEE Trans. Inf. Theory 60(7), 3797–3820 (2014)CrossRefGoogle Scholar

Copyright information

© International Association for Cryptologic Research 2016

Authors and Affiliations

  1. 1.John A. Paulson School of Engineering and Applied SciencesHarvard UniversityCambridgeUSA
  2. 2.IBM, Almaden Research CenterSan JoseUSA

Personalised recommendations