A learning theory approach to non-interactive database privacy

Avrim Blum*, Katrina Liqett, Aaron Roth

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

293 Scopus citations

Abstract

We demonstrate that, ignoring computational constraints, it is possible to release privacy-preserving databases that are useful for all queries over a discretized domain from any given concept class with polynomial VC-dimension. We show a new lower bound for releasing databases that are useful for halfspace queries over a continuous domain. Despite this, we give a privacy-preserving polynomial time algorithm that releases information useful for all half-space queries, for a slightly relaxed definition of usefulness. Inspired by learning theory, we introduce a new notion of data privacy, which we call distributional privacy, and show that it is strictly stronger than the prevailing privacy notion, differential privacy.

Original languageAmerican English
Title of host publicationSTOC'08
Subtitle of host publicationProceedings of the 2008 ACM Symposium on Theory of Computing
PublisherAssociation for Computing Machinery
Pages609-617
Number of pages9
ISBN (Print)9781605580470
DOIs
StatePublished - 2008
Externally publishedYes
Event40th Annual ACM Symposium on Theory of Computing, STOC 2008 - Victoria, BC, Canada
Duration: 17 May 200820 May 2008

Publication series

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

Conference

Conference40th Annual ACM Symposium on Theory of Computing, STOC 2008
Country/TerritoryCanada
CityVictoria, BC
Period17/05/0820/05/08

Keywords

  • Learning theory
  • Non-interactive database privacy

Fingerprint

Dive into the research topics of 'A learning theory approach to non-interactive database privacy'. Together they form a unique fingerprint.

Cite this