Paper 2011/071

Information-theoretic Bounds for Differentially Private Mechanisms

Gilles Barthe and Boris Köpf


There are two active and independent lines of research that aim at quantifying the amount of information that is disclosed by computing on confidential data. Each line of research has developed its own notion of confidentiality: on the one hand, differential privacy is the emerging consensus guarantee used for privacy-preserving data analysis. On the other hand, information-theoretic notions of leakage are used for characterizing the confidentiality properties of programs in language-based settings. The purpose of this article is to establish formal connections between both notions of confidentiality, and to compare them in terms of the security guarantees they deliver. We obtain the following results. First, we establish upper bounds for the leakage of every $\eps$-differentially private mechanism in terms of~$\eps$ and the size of the mechanism's input domain. We achieve this by identifying and leveraging a connection to coding theory. Second, we construct a class of $\eps$-differentially private channels whose leakage grows with the size of their input domains. Using these channels, we show that there cannot be domain-size-independent bounds for the leakage of all $\eps$-differentially private mechanisms. Moreover, we perform an empirical evaluation that shows that the leakage of these channels almost matches our theoretical upper bounds, demonstrating the accuracy of these bounds. Finally, we show that the question of providing optimal upper bounds for the leakage of $\eps$-differentially private mechanisms in terms of rational functions of $\eps$ is in fact decidable.

Available format(s)
Publication info
Published elsewhere. Accepted for publication at CSF '11
Differential PrivacyInformation theory.
Contact author(s)
boris koepf @ imdea org
2011-04-25: revised
2011-02-14: received
See all versions
Short URL
Creative Commons Attribution


      author = {Gilles Barthe and Boris Köpf},
      title = {Information-theoretic Bounds for Differentially Private Mechanisms},
      howpublished = {Cryptology ePrint Archive, Paper 2011/071},
      year = {2011},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.