no code implementations • 8 Dec 2023 • Georgi Ganev, Emiliano De Cristofaro
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.
no code implementations • 9 Jul 2023 • Lauren Arthur, Jason Costello, Jonathan Hardy, Will O'Brien, James Rea, Gareth Rees, Georgi Ganev
Generative AI technologies are gaining unprecedented popularity, causing a mix of excitement and apprehension through their remarkable capabilities.
no code implementations • 1 Jul 2023 • Georgi Ganev
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.
no code implementations • 18 May 2023 • Georgi Ganev, Kai Xu, Emiliano De Cristofaro
Generative models trained with Differential Privacy (DP) are increasingly used to produce synthetic data while reducing privacy risks.
2 code implementations • 12 Jul 2022 • Sofiane Mahiou, Kai Xu, Georgi Ganev
We propose a general, flexible, and scalable framework dpart, an open source Python library for differentially private synthetic data generation.
no code implementations • 26 Nov 2021 • Georgi Ganev
Generative Adversarial Networks (GANs) are among the most popular approaches to generate synthetic data, especially images, for data sharing purposes.
no code implementations • 23 Sep 2021 • Georgi Ganev, Bristena Oprisanu, Emiliano De Cristofaro
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.
no code implementations • 5 Feb 2021 • Bristena Oprisanu, Georgi Ganev, Emiliano De Cristofaro
The availability of genomic data is essential to progress in biomedical research, personalized medicine, etc.