Year: 2020
Type: article
Abstract: 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 private artificial data samples and empirically assess the risk of information disclosure. Our experiments show that FedGP is able to generate labeled 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.
Source: IEEE Intelligent Systems
Authors: Aleksei Triastcyn, Boi Faltings
Institution: École Polytechnique Fédérale de Lausanne
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2980772046
