On the Contractivity of Privacy Mechanisms

We present a novel way to compare the statistical cost of privacy mechanisms using their Dobrushin coefficient. Specifically, we provide upper and lower bounds for the Dobrushin coefficient of a privacy mechanism in terms of its maximal leakage and local differential privacy guarantees. Given the geometric nature of the Dobrushin coefficient, this approach provides some insights into the general statistical cost of these privacy guarantees. We highlight the strength of this method by applying our results to develop new bounds on the $\ell_2$-minimax risk in a distribution estimation setting under maximal leakage constraints. Specifically, we find its order with respect to the sample size and privacy level, allowing a quantitative comparison with the corresponding local differential privacy $\ell_2$-minimax risk.

[1]  Yihong Wu,et al.  Dissipation of Information in Channels With Input Constraints , 2014, IEEE Transactions on Information Theory.

[2]  Sudeep Kamath,et al.  An operational measure of information leakage , 2016, 2016 Annual Conference on Information Science and Systems (CISS).

[3]  Lizhong Zheng,et al.  Linear Bounds between Contraction Coefficients for $f$-Divergences , 2015, 1510.01844.

[4]  Martin J. Wainwright,et al.  Local privacy and statistical minimax rates , 2013, 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[5]  Lizhong Zheng,et al.  Bounds between contraction coefficients , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[6]  Alon Orlitsky,et al.  On Learning Distributions from their Samples , 2015, COLT.

[7]  V. Tan,et al.  Hypothesis testing under maximal leakage privacy constraints , 2017, 2017 IEEE International Symposium on Information Theory (ISIT).

[8]  Alexander Barg,et al.  Asymptotically optimal private estimation under mean square loss , 2017, ArXiv.

[9]  Martin J. Wainwright,et al.  Minimax Optimal Procedures for Locally Private Estimation , 2016, ArXiv.

[10]  Michael Gastpar,et al.  Locally differentially-private distribution estimation , 2016, 2016 IEEE International Symposium on Information Theory (ISIT).

[11]  R. Dobrushin Central Limit Theorem for Nonstationary Markov Chains. II , 1956 .

[12]  Pramod Viswanath,et al.  Extremal Mechanisms for Local Differential Privacy , 2014, J. Mach. Learn. Res..