12 papers
ReBound: Reuse-Aware Privacy For Interactive Decision Support
Nada Lahjouji, Shufan Zhang, Xi He +1
ReBound is a framework that reuses cached results from earlier differentially private queries to answer new interactive decision‑support queries with reduced or zero additional pri…
MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
Masoumeh Shafieinejad, Xi He, Mahshid Alinoori +6
Synthetic data is often perceived as a silver-bullet solution to data anonymization and privacy-preserving data publishing. Drawn from generative models like diffusion models, synt…
FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models
Abtin Mahyar, Masoumeh Shafieinejad, Yuhan Liu +1
Diffusion models are the leading approach for tabular data synthesis and are increasingly used to share sensitive records. Whether they actually protect privacy has become a pressi…
On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
Masoumeh Shafieinejad, D. B. Emerson, Behnoosh Zamanlooy +5
Tabular data plays an important role in many fields and industries, including those with elevated privacy considerations and risks. As such, there is a rising interest in generatin…
Interpreting the Error of Differentially Private Median Queries through Randomization Intervals
Thomas Humphries, Tim Li, Shufan Zhang +2
It can be difficult for practitioners to interpret the quality of differentially private (DP) statistics due to the added noise. One method to help analysts understand the amount o…
GPM: The Gaussian Pancake Mechanism for Planting Undetectable Backdoors in Differential Privacy
Haochen Sun, Xi He
Differential privacy (DP) has become the gold standard for preserving individual privacy in data analysis. However, an implicit yet fundamental assumption underlying these rigorous…