Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds

@article{Bun2016ConcentratedDP,
  title={Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds},
  author={Mark Bun and Thomas Steinke},
  journal={ArXiv},
  year={2016},
  volume={abs/1605.02065}
}
"Concentrated differential privacy" was recently introduced by Dwork and Rothblum as a relaxation of differential privacy, which permits sharper analyses of many privacy-preserving computations. We present an alternative formulation of the concept of concentrated differential privacy in terms of the Renyi divergence between the distributions obtained by running an algorithm on neighboring inputs. With this reformulation in hand, we prove sharper quantitative results, establish lower bounds, and… 
Rényi Differential Privacy
  • Ilya Mironov
  • Computer Science
    2017 IEEE 30th Computer Security Foundations Symposium (CSF)
  • 2017
TLDR
This work argues that the useful analytical tool can be used as a privacy definition, compactly and accurately representing guarantees on the tails of the privacy loss, and demonstrates that the new definition shares many important properties with the standard definition of differential privacy.
Reasoning about Divergences for Relaxations of Differential Privacy
We develop a semantics framework for verifying recent relaxations of differential privacy: R\'enyi differential privacy and zero-concentrated differential privacy. Both notions require a bound on a
Approximate Span Liftings: Compositional Semantics for Relaxations of Differential Privacy
We develop new abstractions for reasoning about three relaxations of differential privacy: $R$ényi differential privacy, zero-concentrated differential privacy, and truncated concentrated
Gaussian differential privacy
TLDR
The privacy guarantees of any hypothesis testing based definition of privacy (including the original differential privacy definition) converges to GDP in the limit under composition and a Berry–Esseen style version of the central limit theorem is proved, which gives a computationally inexpensive tool for tractably analysing the exact composition of private algorithms.
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
TLDR
This work introduces a family of analytical and sharp privacy bounds under composition using the Edgeworth expansion in the framework of the recently proposed f-differential privacy to address a fundamental question in differential privacy regarding how the overall privacy bound degrades under composition.
Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences
TLDR
This paper presents a general method that recovers and improves prior analyses, yields lower bounds and derives new instances of privacy amplification by subsampling, which leverages a characterization of differential privacy as a divergence which emerged in the program verification community.
Composable and versatile privacy via truncated CDP
TLDR
This new definition of truncated concentrated differential privacy provides robust and efficient composition guarantees, supports powerful algorithmic techniques such as privacy amplification via sub-sampling, and enables more accurate statistical analyses.
PrivacyBuDe: Privacy Buckets Demo Tight Differential Privacy Guarantees made Simple
TLDR
This work provides an easy-to-use interface for computing state-of-the-art differential privacy guarantees by simply accessing a website and guaranteeing the scale parameter of the noise, the sensitivity, and the number of compositions for the widely used Laplace mechanism and the similarly popular Gauss mechanism.
Local Differential Privacy Is Equivalent to Contraction of $E_\gamma$-Divergence
TLDR
This work shows that LDP constraints can be equivalently cast in terms of the contraction coefficient of the Eγ-divergence, and uses this equivalent formula to express LDP guarantees of privacy mechanisms in Terms of contraction coefficients of arbitrary f -divergences.
Privacy Loss Classes: The Central Limit Theorem in Differential Privacy
TLDR
This paper shows that for non-adaptive mechanisms, the privacy loss under sequential composition undergoes a convolution and will converge to a Gauss distribution (the central limit theorem for DP) and derives several relevant insights.
...
...

References

SHOWING 1-10 OF 34 REFERENCES
The Composition Theorem for Differential Privacy
TLDR
This paper proves an upper bound on the overall privacy level and construct a sequence of privatization mechanisms that achieves this bound by introducing an operational interpretation of differential privacy and the use of a data processing inequality.
The Limits of Two-Party Differential Privacy
TLDR
Borders expose a dramatic gap between the accuracy that can be obtained by differentially private data analysis versus the accuracy obtainable when privacy is relaxed to a computational variant of differential privacy.
Private Learning and Sanitization: Pure vs. Approximate Differential Privacy
TLDR
It is shown that the sample complexity of private learning and sanitization tasks under approximate differential privacy can be significantly lower than that under pure differential privacy.
Concentrated Differential Privacy
We introduce Concentrated Differential Privacy, a relaxation of Differential Privacy enjoying better accuracy than both pure differential privacy and its popular "(epsilon,delta)" relaxation without
Between Pure and Approximate Differential Privacy
TLDR
New purely and approximately differentially private algorithms for answering arbitrary statistical queries that improve on the sample complexity of the standard Laplace and Gaussian mechanisms for achieving worst-case accuracy guarantees by a logarithmic factor are given.
The Algorithmic Foundations of Differential Privacy
TLDR
The preponderance of this monograph is devoted to fundamental techniques for achieving differential privacy, and application of these techniques in creative combinations, using the query-release problem as an ongoing example.
Fingerprinting codes and the price of approximate differential privacy
TLDR
The results rely on the existence of short fingerprinting codes (Boneh and Shaw, CRYPTO'95; Tardos, STOC'03), which are closely connected to the sample complexity of differentially private data release.
On the geometry of differential privacy
TLDR
The lower bound is strong enough to separate the concept of differential privacy from the notion of approximate differential privacy where an upper bound of O(√{d}/ε) can be achieved.
Lower Bounds in Differential Privacy
TLDR
This paper combines the techniques of Hardt and Talwar [11] and McGregor et al.
The Complexity of Computing the Optimal Composition of Differential Privacy
TLDR
Since computing optimal composition exactly is infeasible unless FP=#P, this work gives an approximation algorithm that computes the composition to arbitrary accuracy in polynomial time and shows that computing the optimal composition in general is #P-complete.
...
...