Connect the dots: Dataset Condensation, Differential Privacy, and Adversarial Uncertainty

arXiv:2402.10423v1 Announce Type: new
Abstract: Our work focuses on understanding the underpinning mechanism of dataset condensation by drawing connections with ($\epsilon$, $\delta$)-differential privacy where the optimal noise, $\epsilon$, is chosen by adversarial uncertainty \cite{Grining2017}. We can answer the question about the inner workings of the dataset condensation procedure. Previous work \cite{dong2022} proved the link between dataset condensation (DC) and ($\epsilon$, $\delta$)-differential privacy. However, it is unclear from existing works on ablating DC to obtain a lower-bound estimate of $\epsilon$ that …

adversarial arxiv can connect connections connect the dots cs.ai cs.cr dataset delta differential privacy drawing mechanism noise privacy procedure question uncertainty understanding work