On maximal correlation, mutual information and data privacy

The rate-privacy function is defined in [1] as a tradeoff between privacy and utility in a distributed private data system in which both privacy and utility are measured using mutual information. Here, we use maximal correlation in lieu of mutual information in the privacy constraint. We first obtain some general properties and bounds for maximal correlation and then modify the rate-privacy function to account for the privacy-constrained estimation problem. We find a bound for the utility in this problem when the maximal correlation privacy is set to some threshold ϵ > 0 and construct an explicit privacy scheme which achieves this bound.

[1]  Shan Lu,et al.  MEASURING DEPENDENCE VIA MUTUAL INFORMATION , 2011 .

[2]  R. Gray.  Entropy and Information Theory , 1990, Springer New York.

[3]  Venkat Anantharam,et al.  Non-interactive simulation of joint distributions: The Hirschfeld-Gebelein-Rényi maximal correlation and the hypercontractivity ribbon , 2012, 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[4]  Alexandre V. Evfimievski,et al.  Limiting privacy breaches in privacy preserving data mining , 2003, PODS.

[5]  Venkat Anantharam,et al.  On Maximal Correlation, Hypercontractivity, and the Data Processing Inequality studied by Erkip and Cover , 2013, ArXiv.

[6]  Shao-Lun Huang,et al.  Linear information coupling problems , 2012, 2012 IEEE International Symposium on Information Theory Proceedings.

[7]  Amin Gohari,et al.  On the duality of additivity and tensorization , 2015, 2015 IEEE International Symposium on Information Theory (ISIT).

[8]  Hirosuke Yamamoto,et al.  A source coding problem for sources with additional outputs to keep secret from the receiver or wiretappers , 1983, IEEE Trans. Inf. Theory.

[9]  E. H. Linfoot.  An Informational Measure of Correlation , 1957, Inf. Control..

[10]  Amin Gohari,et al.  Monotone Measures for Non-Local Correlations , 2014, IEEE Transactions on Information Theory.

[11]  Reza Modarres,et al.  Measures of Dependence , 2011, International Encyclopedia of Statistical Science.

[12]  H. O. Lancaster.  Some properties of the bivariate normal distribution considered in the form of a contingency table , 1957 .

[13]  Rohit Negi,et al.  Guaranteeing Secrecy using Artificial Noise , 2008, IEEE Transactions on Wireless Communications.

[14]  R. Durrett.  Probability: Theory and Examples , 1993 .

[15]  A. Dembo,et al.  On the Maximum Correlation Coefficient , 2005 .

[16]  Meir Feder,et al.  The uniform distribution as a universal prior , 2004, IEEE Transactions on Information Theory.

[17]  H. Witsenhausen.  ON SEQUENCES OF PAIRS OF DEPENDENT RANDOM VARIABLES , 1975 .

[18]  Imre Csiszár,et al.  Information Theory - Coding Theorems for Discrete Memoryless Systems, Second Edition , 2011 .

[19]  Fady Alajaji,et al.  Notes on information-theoretic privacy , 2014, 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton).