Search Results for author:
Found 8 papers, 1 papers with code
On the Inadequacy of Similarity-based Privacy Metrics: Reconstruction Attacks against "Truly Anonymous Synthetic Data''
Alas, this is not the standard in industry as many companies use ad-hoc strategies to empirically evaluate privacy based on the statistical similarity between synthetic and real data.
On the Challenges of Deploying Privacy-Preserving Synthetic Data in the Enterprise
Generative AI technologies are gaining unprecedented popularity, causing a mix of excitement and apprehension through their remarkable capabilities.
When Synthetic Data Met Regulation
In this paper, we argue that synthetic data produced by Differentially Private generative models can be sufficiently anonymized and, therefore, anonymous data and regulatory compliant.
Understanding how Differentially Private Generative Models Spend their Privacy Budget
Generative models trained with Differential Privacy (DP) are increasingly used to produce synthetic data while reducing privacy risks.
dpart: Differentially Private Autoregressive Tabular, a General Framework for Synthetic Data Generation
We propose a general, flexible, and scalable framework dpart, an open source Python library for differentially private synthetic data generation.
DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?
Generative Adversarial Networks (GANs) are among the most popular approaches to generate synthetic data, especially images, for data sharing purposes.
Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data
We analyze the impact of DP on these models vis-a-vis underrepresented classes/subgroups of data, specifically, studying: 1) the size of classes/subgroups in the synthetic data, and 2) the accuracy of classification tasks run on them.
On Utility and Privacy in Synthetic Genomic Data
The availability of genomic data is essential to progress in biomedical research, personalized medicine, etc.
