An official website of the United States government
Protection of individual privacy is a common concern when releasing and sharing data and information. Differential privacy (DP) formalizes privacy in probabilistic terms without making assumptions about the background knowledge of data intruders, and thus provides a robust concept for privacy protection. Practical applications of DP involve development of differentially private mechanisms to generate sanitized results at a pre-specified privacy budget. For the sanitization of statistics with publicly known bounds such as proportions and correlation coefficients, the bounding constraints will need to be incorporated in the differentially private mechanisms. There has been little work on examining the consequences of the bounding constraints on the accuracy of sanitized results and the statistical inferences of the population parameters based on the sanitized results. In this paper, we formalize the differentially private truncated and boundary inflated truncated (BIT) procedures for releasing statistics with publicly known bounding constraints. The impacts of the truncated and BIT Laplace procedures on the statistical accuracy and validity of sanitized statistics are evaluated both theoretically and empirically via simulation studies.
more »
« less
Inference for Optimal Differential Privacy Procedures for Frequency Tables
When releasing data to the public, a vital concern is the risk of exposing personal information of the individuals who have contributed to the data set. Many mechanisms have been proposed to protect individual privacy, though less attention has been dedicated to practically conducting valid inferences on the altered privacy-protected data sets. For frequency tables, the privacy-protection-oriented perturbations often lead to negative cell counts. Releasing such tables can undermine users’ confidence in the usefulness of such data sets. This paper focuses on releasing one-way frequency tables. We recommend an optimal mechanism that satisfies ϵ-differential privacy (DP) without suffering from having negative cell counts. The procedure is optimal in the sense that the expected utility is maximized under a given privacy constraint. Valid inference procedures for testing goodness-of-fit are also developed for the DP privacy-protected data. In particular, we propose a de-biased test statistic for the optimal procedure and derive its asymptotic distribution. In addition, we also introduce testing procedures for the commonly used Laplace and Gaussian mechanisms, which provide a good finite sample approximation for the null distributions. Moreover, the decaying rate requirements for the privacy regime are provided for the inference procedures to be valid. We further consider common users’ practices such as merging related or neighboring cells or integrating statistical information obtained across different data sources and derive valid testing procedures when these operations occur. Simulation studies show that our inference results hold well even when the sample size is relatively small. Comparisons with the current field standards, including the Laplace, the Gaussian (both with/without post-processing of replacing negative cell counts with zeros), and the Binomial-Beta McClure-Reiter mechanisms, are carried out. In the end, we apply our method to the National Center for Early Development and Learning’s (NCEDL) multi-state studies data to demonstrate its practical applicability.
more »
« less
- Award ID(s):
- 1846747
- PAR ID:
- 10331529
- Date Published:
- Journal Name:
- Journal of Data Science
- ISSN:
- 1680-743X
- Page Range / eLocation ID:
- 253 to 276
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
To quantify trade-offs between increasing demand for open data sharing and concerns about sensitive information disclosure, statistical data privacy (SDP) methodology analyzes data release mechanisms that sanitize outputs based on confidential data. Two dominant frameworks exist: statistical disclosure control (SDC) and the more recent differential privacy (DP). Despite framing differences, both SDC and DP share the same statistical problems at their core. For inference problems, either we may design optimal release mechanisms and associated estimators that satisfy bounds on disclosure risk measures, or we may adjust existing sanitized output to create new statistically valid and optimal estimators. Regardless of design or adjustment, in evaluating risk and utility, valid statistical inferences from mechanism outputs require uncertainty quantification that accounts for the effect of the sanitization mechanism that introduces bias and/or variance. In this review, we discuss the statistical foundations common to both SDC and DP, highlight major developments in SDP, and present exciting open research problems in private inference.more » « less
-
Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; Oh, A. (Ed.)A canonical noise distribution (CND) is an additive mechanism designed to satisfy f-differential privacy (f-DP), without any wasted privacy budget. f-DP is a hypothesis testing-based formulation of privacy phrased in terms of tradeoff functions, which captures the difficulty of a hypothesis test. In this paper, we consider the existence and construction of both log-concave CNDs and multivariate CNDs. Log-concave distributions are important to ensure that higher outputs of the mechanism correspond to higher input values, whereas multivariate noise distributions are important to ensure that a joint release of multiple outputs has a tight privacy characterization. We show that the existence and construction of CNDs for both types of problems is related to whether the tradeoff function can be decomposed by functional composition (related to group privacy) or mechanism composition. In particular, we show that pure epsilon-DP cannot be decomposed in either way and that there is neither a log-concave CND nor any multivariate CND for epsilon-DP. On the other hand, we show that Gaussian-DP, (0,delta)-DP, and Laplace-DP each have both log-concave and multivariate CNDs.more » « less
-
Wang, H; Xiao, X (Ed.)Differential privacy (DP) is applied when fine-tuning pre-trained language models (LMs) to limit leakage of training examples. While most DP research has focused on improving a model’s privacy-utility tradeoff, some find that DP can be unfair to or biased against underrepresented groups. In this work, we extensively analyze the impact of DP on bias in LMs. We find differentially private training can increase the model bias against protected groups w.r.t AUC-based bias metrics. DP makes it more difficult for the model to differentiate between the positive and negative examples from the protected groups and other groups in the rest of the population. Our results also show that the impact of DP on bias is affected by both the privacy protection level and the underlying distribution of the dataset.more » « less
-
Bun, Mark (Ed.)Given a differentially private unbiased estimate q̃ = q(D) +ν of a statistic q(D), we wish to obtain unbiased estimates of functions of q(D), such as 1/q(D), solely through post-processing of q̃, with no further access to the confidential dataset D. To this end, we adapt the deconvolution method used for unbiased estimation in the statistical literature, deriving unbiased estimators for a broad family of twice-differentiable functions - those that are tempered distributions - when the privacy-preserving noise ν is drawn from the Laplace distribution (Dwork et al., 2006). We further extend this technique to functions other than tempered distributions, deriving approximately optimal estimators that are unbiased for values in a user-specified interval (possibly extending to ± ∞). We use these results to derive an unbiased estimator for private means when the size n of the dataset is not publicly known. In a numerical application, we find that a mechanism that uses our estimator to return an unbiased sample size and mean outperforms a mechanism that instead uses the previously known unbiased privacy mechanism for such means (Kamath et al., 2023). We also apply our estimators to develop unbiased transformation mechanisms for per-record differential privacy, a privacy concept in which the privacy guarantee is a public function of a record’s value (Seeman et al., 2024). Our mechanisms provide stronger privacy guarantees than those in prior work (Finley et al., 2024) by using Laplace, rather than Gaussian, noise. Finally, using a different approach, we go beyond Laplace noise by deriving unbiased estimators for polynomials under the weak condition that the noise distribution has sufficiently many moments.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.6339/22-JDS1044
