Training generative models from privatized data
Local differential privacy is a powerful method for privacy-preserving data collection. In this paper, we develop a framework for training Generative Adversarial Networks (GANs) on differentially privatized data. We show that entropic regularization of optimal transport - a popular regularization method in the literature that has often been leveraged for its computational benefits - enables the generator to learn the raw (unprivatized) data distribution even though it only has access to privatized samples. We prove that at the same time this leads to fast statistical convergence at the parametric rate. This shows that entropic regularization of optimal transport uniquely enables the mitigation of both the effects of privatization noise and the curse of dimensionality in statistical convergence. We provide experimental evidence to support the efficacy of our framework in practice.
Code (0)
등록된 구현이 없습니다.
Tasks
Privacy PreservingSimilar Papers 제목 키워드 기반
DP-BART for Privatized Text Rewriting under Local Differential Privacy
Privatized text rewriting with local differential privacy (LDP) is a recent approach that enables sharing of sensitive textual documents while formally guaranteeing privacy protection to individuals. However, existing sy…
text-classificationText ClassificationReconXF: Graph Reconstruction Attack via Public Feature Explanations on Privatized Node Features and Labels
Graph Neural Networks (GNNs) achieve high performance across many applications but function as black-box models, limiting their use in critical domains like healthcare and criminal justice. Explainability methods address…
DenoisingGraph ReconstructionReconstruction AttackBayesian Frequency Estimation Under Local Differential Privacy With an Adaptive Randomized Response Mechanism
Frequency estimation plays a critical role in many applications involving personal and private categorical data. Such data are often collected sequentially over time, making it valuable to estimate their distribution onl…
Nonparametric extensions of randomized response for private confidence sets
This work derives methods for performing nonparametric, nonasymptotic statistical inference for population means under the constraint of local differential privacy (LDP). Given bounded observations $(X_1, \dots, X_n)$ wi…
DP-FedSOFIM: Differentially Private Federated Stochastic Optimization using Regularized Fisher Information Matrix
Differentially private federated learning (DP-FL) often suffers from slow convergence under tight privacy budgets because the noise required for privacy preservation degrades gradient quality. Although second-order optim…
Stochastic OptimizationFederated Learning