A statistical framework for differential privacy

DOI10.1198/JASA.2009.TM08651MaRDI QIDQ5254963zbMATH OpenOpenAlexWikidataFDO

Authors Shuheng Zhou, Larry Wasserman

Publication date 11 June 2015

Published in Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0811.2501

zbMATH Keywords

differential privacy

Mathematics Subject Classification ID

Large deviations (60F10) Statistical aspects of information-theoretic topics (62B10) Authentication, digital signatures and secret sharing (94A62)

Abstract: One goal of statistical privacy research is to construct a data release mechanism that protects individual privacy while preserving information content. An example is a {em random mechanism} that takes an input database $X$ and outputs a random database $Z$ according to a distribution $Q_n(cdot|X)$. {em Differential privacy} is a particular privacy requirement developed by computer scientists in which $Q_n(cdot|X)$ is required to be insensitive to changes in one data point in $X$. This makes it difficult to infer from $Z$ whether a given individual is in the original database $X$. We consider differential privacy from a statistical perspective. We consider several data release mechanisms that satisfy the differential privacy requirement. We show that it is useful to compare these schemes by computing the rate of convergence of distributions and densities constructed from the released data. We study a general privacy method, called the exponential mechanism, introduced by McSherry and Talwar (2007). We show that the accuracy of this method is intimately linked to the rate at which the probability that the empirical distribution concentrates in a small ball around the true distribution.

Recommendations

• Universally utility-maximizing privacy mechanisms
• Universally utility-maximizing privacy mechanisms
• Differential Privacy
• The algorithmic foundations of differential privacy
• Privacy-preserving statistical estimation with optimal convergence rates

Cited in

(99)

• Confidentiality and differential privacy in the dissemination of frequency tables
• Data confidentiality: a review of methods for statistical disclosure limitation and methods for assessing privacy
• On density estimation at a fixed point under local differential privacy
• Strongly universally consistent nonparametric regression and classification with privatised data
• The cost of privacy: optimal rates of convergence for parameter estimation with differential privacy
• On the power of multiple anonymous messages: frequency estimation and selection in the shuffle model of differential privacy
• Differentially private data release via statistical election to partition sequentially
• Obtaining minimax lower bounds: a review
• Local differential privacy: elbow effect in optimal density estimation and adaptation over Besov ellipsoids
• Geometrizing rates of convergence under local differential privacy constraints
• Comparative study of differentially private data synthesis methods
• Exact MCMC with differentially private moves. Exact MCMC with differentially private moves, revisiting the penalty algorithm in a data privacy framework
• Extreme points of the local differential privacy polytope
• Worst- and average-case privacy breaches in randomization mechanisms
• Worst- and average-case privacy breaches in randomization mechanisms
• scientific article; zbMATH DE number 7234802 (Why is no real title available?)
• Differentially private response mechanisms on categorical data
• Differentially Private Significance Tests for Regression Coefficients
• Private and continual release of statistics
• New Efficient Attacks on Statistical Disclosure Control Mechanisms
• Asymptotically Optimal and Private Statistical Estimation
• Differential privacy based on importance weighting
• Minimax Optimal Procedures for Locally Private Estimation
• Comment
• Universally utility-maximizing privacy mechanisms
• Finite sample differentially private confidence intervals
• Structure and sensitivity in differential privacy: comparing \(K\)-norm mechanisms
• Privacy-preserving parametric inference: a case for robust statistics
• The complexity of differential privacy
• Private sequential learning
• Nonparametric density estimation for intentionally corrupted functional data
• Directed Networks with a Differentially Private Bi-degree Sequence
• scientific article; zbMATH DE number 7625208 (Why is no real title available?)
• On the optimality of the exponential mechanism
• Model averaging with privacy-preserving
• scientific article; zbMATH DE number 7415075 (Why is no real title available?)
• Universally utility-maximizing privacy mechanisms
• Differential privacy and robust statistics
• Outlier privacy
• Differential privacy in metric spaces: numerical, categorical and functional data under the one roof
• Information-theoretic foundations of differential privacy
• Differential privacy for Bayesian inference through posterior sampling
• Differential privacy for functions and functional data
• Privacy-preserving statistical estimation with optimal convergence rates
• Differential privacy for the analyst via private equilibrium computation
• Privacy aware learning
• When Random Sampling Preserves Privacy
• Differential Privacy
• Inference using noisy degrees: differentially private -model and synthetic graphs
• Multivariate density estimation from privatised data: universal consistency and minimax rates
• Privacy-preserving federated learning on lattice quantization
• Discrimination of quantum states under locality constraints in the many-copy setting
• Phase transitions for support recovery under local differential privacy
• Distribution-invariant differential privacy
• Goodness-of-fit testing for Hölder continuous densities under local differential privacy
• Divergences on monads for relational program logics
• The right complexity measure in locally private estimation: it is not the Fisher information
• A Feasibility Study of Differentially Private Summary Statistics and Regression Analyses with Evaluations on Administrative and Survey Data
• Density estimation under local differential privacy and Hellinger loss
• Interactive versus noninteractive locally differentially private estimation: two elbows for the quadratic functional
• Canonical noise distributions and private hypothesis tests
• On robustness and local differential privacy
• Differentially private inference via noisy optimization
• Differentially private confidence intervals for proportions under stratified random sampling
• Differentially private outcome-weighted learning for optimal dynamic treatment regime estimation
• Private measures, random walks, and synthetic data
• Edge differentially private estimation in the -model via jittering and method of moments
• Gaussian differentially private robust mean estimation and inference
• Distributed optimal subsampling for quantile regression with massive data
• General inferential limits under differential and pufferfish privacy
• Majority vote for distributed differentially private sign selection
• Efficiency in local differential privacy
• On the power of private likelihood-ratio tests for goodness-of-fit in frequency tables
• A linear type system for L^p-metric sensitivity analysis
• Privacy-preserving federated averaging on heterogeneous data
• MCMC for Bayesian Nonparametric Mixture Modeling Under Differential Privacy
• Advanced composition theorems for differential obliviousness
• Differentially private analysis of networks with covariates via a generalized -model
• Minimax rate for multivariate data under componentwise local differential privacy constraints
• Minimax rates of convergence for sliced inverse regression with differential privacy
• Local differential privacy in survival analysis using private failure indicators
• Distributed empirical likelihood inference with privacy guarantees
• Differentially private multivariate statistics with an application to contingency table analysis
• Differentially private low-dimensional synthetic data from high-dimensional datasets
• Differentially private Kolmogorov-Smirnov-type tests
• A polynomial time, pure differentially private estimator for binary product distributions
• Unbiased statistical estimation and valid confidence intervals under differential privacy
• Mechanisms for global differential privacy under Bayesian data synthesis
• Differentially private histogram with valid statistics
• Differentially private Assouad, Fano, and Le Cam
• Evolving privacy: drift parameter estimation for discretely observed i.i.d. diffusion processes under LDP
• Generating Poisson-distributed differentially private synthetic data
• Versatile differentially private learning for general loss functions
• Federated learning on Riemannian manifolds with differential privacy
• Online differentially private inference for linear regression model
• Locally differentially private two-sample testing
• Differentially Private Sliced Inverse Regression: Minimax Optimality and Algorithm
• Sample-optimal learning of quantum states using gentle measurements
• A firm foundation for statistical disclosure control

This page was built for publication: A statistical framework for differential privacy

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5254963)