No packages match

DPSynth - Differentially Private Synthetic Data with Guaranteed Utility

Differentially private (DP) synthetic data generation for tabular data. Provides DP Gaussian mixture models, DP Gaussian copulas, DP histogram marginals and a Private Aggregation of Teacher Ensembles (PATE) synthesizer for mixed-type data, together with a standardized utility evaluation framework (univariate fidelity, propensity score MSE, multivariate dependence, downstream task performance), empirical disclosure risk auditing (membership inference, attribute disclosure, record linkage) and privacy budget accounting (basic, advanced and Renyi DP composition). The implementation follows Dwork and Roth (2014) <doi:10.1561/0400000042> and Dwork et al. (2006) <doi:10.1007/11681878_14> for the DP mechanisms, Papernot et al. (2017) <doi:10.1145/3133956.3133982> for the PATE synthesizer, and Woo et al. (2009) <doi:10.2202/1557-4679.1203> for the disclosure risk evaluation framework.

Last updated

4.65 score

DPrivStats - Differentially Private Classical Statistical Inference

Implements differentially private (DP) versions of common classical statistical procedures, including descriptive statistics (mean, variance, quantiles, histograms), hypothesis tests (t-test, chi-square, Kolmogorov-Smirnov, one-way ANOVA), and regression (closed-form DP linear regression and DP-SGD for generalized linear models). Provides Laplace and Gaussian mechanisms with analytic calibration, exponential mechanism for medians, privacy-aware confidence intervals that account for both sampling and privacy noise, and privacy budget accounting via basic, advanced, and Renyi differential privacy (RDP) composition. Designed for official statistics and privacy-preserving data analysis research.

Last updated

cpp

4.65 score 6 scripts 383 downloads