all AI news
Quantifying and Mitigating Privacy Risks for Tabular Generative Models
March 13, 2024, 4:42 a.m. | Chaoyi Zhu, Jiayi Tang, Hans Brouwer, Juan F. P\'erez, Marten van Dijk, Lydia Y. Chen
cs.LG updates on arXiv.org arxiv.org
Abstract: Synthetic data from generative models emerges as the privacy-preserving data-sharing solution. Such a synthetic data set shall resemble the original data without revealing identifiable private information. The backbone technology of tabular synthesizers is rooted in image generative models, ranging from Generative Adversarial Networks (GANs) to recent diffusion models. Recent prior work sheds light on the utility-privacy tradeoff on tabular data, revealing and quantifying privacy risks on synthetic data. We first conduct an exhaustive empirical analysis, …
abstract adversarial arxiv cs.cr cs.lg data data set gans generative generative adversarial networks generative models image information networks privacy resemble risks set solution synthetic synthetic data tabular technology type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US