• Corpus ID: 14861086

Concentrated Differential Privacy

@article{Dwork2016ConcentratedDP,
  title={Concentrated Differential Privacy},
  author={Cynthia Dwork and Guy N. Rothblum},
  journal={ArXiv},
  year={2016},
  volume={abs/1603.01887}
}
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 compromising on cumulative privacy loss over multiple computations. 

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.

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.

Synthetic Data Generation with Differential Privacy via Bayesian Networks

TLDR
PrivBayes, a differentially private method for generating synthetic datasets that was used in the 2018 Differential Privacy Synthetic Data Challenge organized by NIST, is described.

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.

Stronger Privacy Amplification by Shuffling for Rényi and Approximate Differential Privacy

TLDR
The shuffle model of differential privacy has gained significant interest as an intermediate trust model between the standard local and central models and leads to tighter numerical bounds in all parameter settings.

Renyi Differential Privacy Mechanisms for Posterior Sampling

TLDR
This work re-examine the inherent privacy of releasing a single sample from a posterior distribution and proposes novel RDP mechanisms as well as offering a new RDP analysis for an existing method in order to add value to the RDP framework.

Individual Differential Privacy: A Utility-Preserving Formulation of Differential Privacy Guarantees

TLDR
This paper argues that the standard formalization of differential privacy is stricter than required by the intuitive privacy guarantee it seeks, and proposes individual differential privacy, an alternative differential privacy notion that offers the same privacy guarantees as standard differential privacy to individuals (even though not to groups of individuals).

Algorithms with More Granular Differential Privacy Guarantees

TLDR
This work considers partial differential privacy (DP), which allows quantifying the privacy guarantee on a per- attribute basis, and designs algorithms whose per-attribute privacy parameter is smaller that the best possible privacy parameter for the entire record of a person.

Information-theoretic metrics for Local Differential Privacy protocols

TLDR
New information-theoretic metrics for utility and privacy in local Differential Privacy protocols are introduced, showing how they relate to $\varepsilon$-LDP, the \emph{de facto} standard privacy metric, giving an information- theoretic interpretation to the latter.

Bayesian Differential Privacy for Machine Learning

TLDR
Bayesian differential privacy (BDP) is proposed, which takes into account the data distribution to provide more practical privacy guarantees and derives a general privacy accounting method under BDP, building upon the well-known moments accountant.
...

References

SHOWING 1-10 OF 12 REFERENCES

Differential privacy and robust statistics

We show by means of several examples that robust statistical estimators present an excellent starting point for differentially private estimators. Our algorithms use a new paradigm for differentially

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 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.

Differential Privacy

  • C. Dwork
  • Computer Science
    Encyclopedia of Cryptography and Security
  • 2006
TLDR
A general impossibility result is given showing that a formalization of Dalenius' goal along the lines of semantic security cannot be achieved, which suggests a new measure, differential privacy, which, intuitively, captures the increased risk to one's privacy incurred by participating in a database.

Calibrating Noise to Sensitivity in Private Data Analysis

TLDR
The study is extended to general functions f, proving that privacy can be preserved by calibrating the standard deviation of the noise according to the sensitivity of the function f, which is the amount that any single argument to f can change its output.

Our Data, Ourselves: Privacy Via Distributed Noise Generation

TLDR
This work provides efficient distributed protocols for generating shares of random noise, secure against malicious participants, and introduces a technique for distributing shares of many unbiased coins with fewer executions of verifiable secret sharing than would be needed using previous approaches.

Revealing information while preserving privacy

TLDR
A polynomial reconstruction algorithm of data from noisy (perturbed) subset sums and shows that in order to achieve privacy one has to add perturbation of magnitude (Ω√<i>n</i>).

Boosting and Differential Privacy

TLDR
This work obtains an $O(\eps^2) bound on the {\em expected} privacy loss from a single $\eps$-\dfp{} mechanism, and gets stronger bounds on the expected cumulative privacy loss due to multiple mechanisms, each of which provides $\eps-differential privacy or one of its relaxations, and each ofWhich operates on (potentially) different, adaptively chosen, databases.

Metric characterization of random variables and random processes

Sub-Gaussian and pre-Gaussian random variables Orlicz spaces of random variables Regularity of sample paths of a stochastic process Pre-Gaussian processes Shot noise processes and their properties

Subgaussian random variables : An expository note

In this expository note we explore subgaussian random variables and their basic properties. We also present equivalent formulations of the subgaussian condition, and we discuss briefly the structure