The price of privately releasing contingency tables and the spectra of random matrices with correlated rows

Shiva Prasad Kasiviswanathan, Mark Rudelson, Adam Smith, Jonathan Ullman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

55 Scopus citations

Abstract

Marginal (contingency) tables are the method of choice for government agencies releasing statistical summaries of categorical data. In this paper, we derive lower bounds on how much distortion (noise) is necessary in these tables to ensure the privacy of sensitive data. We extend a line of recent work on impossibility results for private data analysis [9, 12, 13, 15] to a natural and important class of functionalities. Consider a database consisting of n rows (one per individual), each row comprising d binary attributes. For any subset of T attributes of size |T|=k, the marginal table for T has 2k entries; each entry counts how many times in the database a particular setting of these attributes occurs. We provide lower bounds for releasing all d k k-attribute marginal tables under several different notions of privacy. (1) We give efficient polynomial time attacks which allow an adversary to reconstruct sensitive information given insufficiently perturbed marginal table releases. In particular, for a constant k, we obtain a tight bound of Ω̃(min √n, √dk-1) on the average distortion per entry for any mechanism that releases all k-attribute marginals while providing "attribute" privacy (a weak notion implied by most privacy definitions). (2) Our reconstruction attacks require a new lower bound on the least singular value of a random matrix with correlated rows. Let M (k) be a matrix with d k rows formed by taking all possible k-way entry-wise products of an underlying set of d random vectors from {0,1} n. For constant k, we show that the least singular value of M (k) is Ω̃(√dk) with high probability (the same asymptotic bound as for independent rows). (3) We obtain stronger lower bounds for marginal tables satisfying differential privacy. We give a lower bound of Ω̃(min {√n, √ dk), which is tight for n Ω̃ (dk). We extend our analysis to obtain stronger results for mechanisms that add instance-independent noise and weaker results when k is super-constant.

Original languageEnglish (US)
Title of host publicationSTOC'10 - Proceedings of the 2010 ACM International Symposium on Theory of Computing
Pages775-784
Number of pages10
DOIs
StatePublished - Jul 23 2010
Event42nd ACM Symposium on Theory of Computing, STOC 2010 - Cambridge, MA, United States
Duration: Jun 5 2010Jun 8 2010

Publication series

NameProceedings of the Annual ACM Symposium on Theory of Computing
ISSN (Print)0737-8017

Other

Other42nd ACM Symposium on Theory of Computing, STOC 2010
CountryUnited States
CityCambridge, MA
Period6/5/106/8/10

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Kasiviswanathan, S. P., Rudelson, M., Smith, A., & Ullman, J. (2010). The price of privately releasing contingency tables and the spectra of random matrices with correlated rows. In STOC'10 - Proceedings of the 2010 ACM International Symposium on Theory of Computing (pp. 775-784). (Proceedings of the Annual ACM Symposium on Theory of Computing). https://doi.org/10.1145/1806689.1806795