English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

High-dimensional data are widely used in the era of deep learning withnumerous applications. However, certain data which has sensitive informationare not allowed to be shared without privacy protection. In this paper, wepropose a novel differentially private data releasing method calledDifferentially Private Data Publishing with Gaussian Optimized Model Inversion(DPGOMI) to address this issue. Our approach involves mapping private data tothe latent space using a public generator, followed by a lower-dimensionalDP-GAN with better convergence properties. We evaluate the performance ofDPGOMI on standard datasets CIFAR10 and SVHN. Our results show that DPGOMIoutperforms the standard DP-GAN method in terms of Inception Score, Fr\'echetInception Distance, and classification performance, while providing the samelevel of privacy. Our proposed approach offers a promising solution forprotecting sensitive data in GAN training while maintaining high-qualityresults.

DPGOMI: Differentially Private Data Publishing with Gaussian Optimized Model Inversion