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.

Version: 0.1.0
Depends: R (≥ 4.1.0)
Imports: stats, utils, MASS
Suggests: testthat (≥ 3.0.0), knitr, rmarkdown
Published: 2026-09-28
DOI: 10.32614/CRAN.package.DPSynth (may not be active yet)
Author: Mukul Bijalwan [aut, cre], Gunjan Aggarwal [aut], Mukul Jain [aut]
Maintainer: Mukul Bijalwan <mukulbijalwan555 at gmail.com>
BugReports: https://github.com/MukulBijalwan/DPSynth/issues
License: MIT + file LICENSE
URL: https://github.com/MukulBijalwan/DPSynth
NeedsCompilation: no
Materials: README
CRAN checks: DPSynth results

Documentation:

Reference manual: DPSynth.html , DPSynth.pdf
Vignettes: Getting Started with DPSynth (source, R code)
Health Data: Mixed Types and Disclosure Risk (source, R code)
Official Statistics Workflow with PUMS-like Microdata (source, R code)

Downloads:

Package source: DPSynth_0.1.0.tar.gz
Windows binaries: r-devel: not available, r-release: not available, r-oldrel: DPSynth_0.1.0.zip
macOS binaries: r-release (arm64): DPSynth_0.1.0.tgz, r-oldrel (arm64): DPSynth_0.1.0.tgz, r-release (x86_64): DPSynth_0.1.0.tgz, r-oldrel (x86_64): DPSynth_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=DPSynth to link to this page.

mirror server hosted at Truenetwork, Russian Federation.