Differentially Private Synthetic Data with Guaranteed Utility

---

Documentation for package ‘DPSynth’ version 0.1.0

• DESCRIPTION file.
• User guides, package vignettes and other documentation.

Help Pages

acs_pums_sample	ACS PUMS-like sample
adult_sample	Anonymized UCI Adult subsample
audit_attribute_disclosure	Attribute disclosure risk audit
audit_linkage_risk	Record linkage risk audit
audit_membership_risk	Membership inference risk audit
check_synth_budget	Check remaining privacy budget
clip_data	Clip data to bounds
dp_copula_synth	DP Gaussian copula synthesis
dp_gmm_synth	DP Gaussian Mixture Model synthesis
dp_marginals_synth	DP marginal synthesis
dp_pate_synth	PATE synthetic data for discrete / mixed-type data
dp_synthesize	Differentially private synthetic data generation
evaluate_downstream	Downstream task performance (TSTR)
evaluate_multivariate	Multivariate fidelity evaluation
evaluate_propensity	Propensity score utility (pMSE)
evaluate_univariate	Univariate fidelity evaluation
evaluate_utility	Standardized utility evaluation
gaussian_mech	Gaussian mechanism
new_synth_budget	Create a privacy budget tracker
print.dp_synthesis_result	Print a synthesis result
rlaplace	Laplace noise
spend_synth	Spend privacy budget on a step