The first systematization of reconstruction attacks on synthetic tabular data finds that generator choice dominates privacy risk over attack choice, with differential privacy effective only at low budgets and most leakage reflecting population structure rather than memorization.
Aim: An adaptive and iterative mechanism for differentially private synthetic data
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
DPDSyn guides differentially private dataset synthesis with a downstream-task model trained under DP, yielding higher accuracy and faster generation than prior distribution-selection methods.
ResidualPlanner provides an optimal scalable matrix mechanism for Gaussian noise on marginal queries that optimizes convex loss functions of variances, with ResidualPlanner+ extending support to combined marginal and range/prefix-sum workloads while outperforming HDMM.
Tab-PE extends Private Evolution to tabular data with heuristic operators, outperforming AIM by up to 10% classification accuracy and 28x speed on high-order correlation datasets under differential privacy.
PACE-GGM selects poorly approximated covariance entries, measures them privately, and reconstructs the full matrix with a maximum-entropy objective to produce a Gaussian graphical model, yielding lower estimation error than uniform perturbation.
The authors apply the Adaptive Iterative Mechanism to create differentially private synthetic data from the LEMURS wearable and survey dataset and show that epsilon=5 retains useful predictive performance for downstream tasks.
Differentially private synthetic data and seeded agent-based models can separate personal identities from usable financial data while meeting regulatory privacy rules.
citing papers explorer
-
SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)
The first systematization of reconstruction attacks on synthetic tabular data finds that generator choice dominates privacy risk over attack choice, with differential privacy effective only at low budgets and most leakage reflecting population structure rather than memorization.
-
DPDSyn: Improving Differentially Private Dataset Synthesis for Model Training by Downstream Task Guidance
DPDSyn guides differentially private dataset synthesis with a downstream-task model trained under DP, yielding higher accuracy and faster generation than prior distribution-selection methods.
-
ResidualPlanner+: a scalable matrix mechanism for marginals and beyond
ResidualPlanner provides an optimal scalable matrix mechanism for Gaussian noise on marginal queries that optimizes convex loss functions of variances, with ResidualPlanner+ extending support to combined marginal and range/prefix-sum workloads while outperforming HDMM.
-
Differentially Private Synthetic Data via APIs 4: Tabular Data
Tab-PE extends Private Evolution to tabular data with heuristic operators, outperforming AIM by up to 10% classification accuracy and 28x speed on high-order correlation datasets under differential privacy.
-
Private Adaptive Covariance Estimation via Gaussian Graphical Models
PACE-GGM selects poorly approximated covariance entries, measures them privately, and reconstructs the full matrix with a maximum-entropy objective to produce a Gaussian graphical model, yielding lower estimation error than uniform perturbation.
-
Aim High, Stay Private: Differentially Private Synthetic Data Enables Public Release of Behavioral Health Information with High Utility
The authors apply the Adaptive Iterative Mechanism to create differentially private synthetic data from the LEMURS wearable and survey dataset and show that epsilon=5 retains useful predictive performance for downstream tasks.
-
Decoupling Identity from Utility: Privacy-by-Design Frameworks for Financial Ecosystems
Differentially private synthetic data and seeded agent-based models can separate personal identities from usable financial data while meeting regulatory privacy rules.