AI Chat AI Image Generator AI Video Text to Speech

Federated Generative Privacy

10/18/2019

∙

by Aleksei Triastcyn, et al.

∙

∙

In this paper, we propose FedGP, a framework for privacy-preserving data release in the federated learning setting. We use generative adversarial networks, generator components of which are trained by FedAvg algorithm, to draw privacy-preserving artificial data samples and empirically assess the risk of information disclosure. Our experiments show that FedGP is able to generate labelled data of high quality to successfully train and validate supervised models. Finally, we demonstrate that our approach significantly reduces vulnerability of such models to model inversion attacks.

Aleksei Triastcyn
8 publications
Boi Faltings
53 publications

research

∙ 10/13/2022

Federated Learning for Tabular Data: Exploring Potential Risk to Privacy

Federated Learning (FL) has emerged as a potentially powerful privacy-pr...

0 Han Wu, et al. ∙

research

∙ 10/18/2019

Privacy-preserving Federated Bayesian Learning of a Generative Model for Imbalanced Classification of Clinical Data

In clinical research, the lack of events of interest often necessitates ...

0 Seok-Ju Hahn, et al. ∙

research

∙ 03/01/2023

FedScore: A privacy-preserving framework for federated scoring system development

We propose FedScore, a privacy-preserving federated learning framework f...

1 Siqi Li, et al. ∙

research

∙ 12/19/2017

Privacy-Preserving Adversarial Networks

We propose a data-driven framework for optimizing privacy-preserving dat...

0 Ardhendu Tripathy, et al. ∙

research

∙ 04/29/2021

Privacy-Preserving Federated Learning on Partitioned Attributes

Real-world data is usually segmented by attributes and distributed acros...

0 Shuang Zhang, et al. ∙

research

∙ 03/01/2021

Federated Learning without Revealing the Decision Boundaries

We consider the recent privacy preserving methods that train the models ...

6 Roozbeh Yousefzadeh, et al. ∙

research

∙ 07/05/2023

Privacy-Preserving Federated Heavy Hitter Analytics for Non-IID Data

Federated heavy-hitter analytics involves the identification of the most...

0 Jiaqi Shao, et al. ∙