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.
TAPAS: a toolbox for adversarial privacy auditing of synthetic data
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 2polarities
background 2representative citing papers
MT-MIA uses heterogeneous graph neural networks under a No-Box model to expose user-level membership leakage in synthetic relational data that single-table attacks underestimate.
A new framework evaluates utility of synthetic mobility trajectories while a membership inference attack reveals privacy vulnerabilities in generative models thought to be safe.
Membership inference attacks adapted from synthetic data succeed on counterfactuals using only the counterfactuals themselves, without model access.
diffGHOST is a conditional diffusion model that segments learned latent space to identify and mitigate memorization of critical trajectory samples, aiming to deliver privacy guarantees alongside data 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.
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.
-
Finding Connections: Membership Inference Attacks for the Multi-Table Synthetic Data Setting
MT-MIA uses heterogeneous graph neural networks under a No-Box model to expose user-level membership leakage in synthetic relational data that single-table attacks underestimate.
-
A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilities
A new framework evaluates utility of synthetic mobility trajectories while a membership inference attack reveals privacy vulnerabilities in generative models thought to be safe.
-
Quantifying the Privacy of Counterfactuals by Leveraging Membership Inference Attacks Against Synthetic Data
Membership inference attacks adapted from synthetic data succeed on counterfactuals using only the counterfactuals themselves, without model access.
-
diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories
diffGHOST is a conditional diffusion model that segments learned latent space to identify and mitigate memorization of critical trajectory samples, aiming to deliver privacy guarantees alongside data utility.
-
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.