A learning theory approach to non-interactive database privacy

  • Authors:
  • Avrim Blum;Katrina Ligett;Aaron Roth

  • Affiliations:
  • Carnegie Mellon, Pittsburgh, PA, USA;Carnegie Mellon, Pittsburgh, PA, USA;Carnegie Mellon, Pittsburgh, PA, USA

  • Venue:
  • STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
  • Year:
  • 2008

Quantified Score

Hi-index 0.02

Visualization

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 halfspace 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.