EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

On the 'Semantics' of Differential Privacy: A Bayesian Formulation

Shiva P. Kasiviswanathan, Adam Smith

Journal of Privacy and Confidentiality · 01.06.2014 · 6 (1)

DOI: 10.29012/jpc.v6i1.634 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Privacy and Confidentiality, online erschienen am 01.06.2014. Verfasst von Shiva P. Kasiviswanathan und 1 weiteren Autor:innen. Die Arbeit wurde bisher 81-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Differential privacy is a definition of privacy for algorithms that analyze and publish information about statistical databases. It is often claimed that differential privacy provides guarantees against adversaries with arbitrary side information. In this paper, we provide a precise formulation of these guarantees in terms of the inferences drawn by a Bayesian adversary. We show that this formulation is satisfied by both epsilon-differential privacy as well as a relaxation known as (epsilon,delta)-differential privacy. Our formulation follows the ideas originally due to Dwork and McSherry. This paper is, to our knowledge, the first place such a formulation appears explicitly. The analysis of the relaxed definition is new to this paper, and provides some guidance for setting the delta parameter when using (epsilon,delta)-differential privacy.

Förderung

  • National Science Foundation

Zitieren

APA

Kasiviswanathan, S. P., & Smith, A. (2014). On the 'Semantics' of Differential Privacy: A Bayesian Formulation. Journal of Privacy and Confidentiality, 6(1). https://doi.org/10.29012/jpc.v6i1.634

Vancouver

Kasiviswanathan SP, Smith A. On the 'Semantics' of Differential Privacy: A Bayesian Formulation. Journal of Privacy and Confidentiality. 2014;6(1). doi:10.29012/jpc.v6i1.634

BibTeX
@article{Kasiviswanathan2014,
  author = {Kasiviswanathan, Shiva P. and Smith, Adam},
  title = {On the 'Semantics' of Differential Privacy: A Bayesian Formulation},
  journal = {Journal of Privacy and Confidentiality},
  year = {2014},
  volume = {6},
  number = {1},
  doi = {10.29012/jpc.v6i1.634}
}
Kostenlos starten →