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

A privacy-preserving adversarial network (PPAN) was recently proposed as aninformation-theoretical framework to address the issue of privacy in datasharing. The main idea of this model was using mutual information as theprivacy measure and adversarial training of two deep neural networks, one asthe mechanism and another as the adversary. The performance of the PPAN modelfor the discrete synthetic data, MNIST handwritten digits, and continuousGaussian data was evaluated compared to the analytically optimal trade-off. Inthis study, we evaluate the PPAN model for continuous non-Gaussian data wherelower and upper bounds of the privacy-preserving problem are used. These boundsinclude the Kraskov (KSG) estimation of entropy and mutual information that isbased on k-th nearest neighbor. In addition to the synthetic data sets, apractical case for hiding the actual electricity consumption from smart meterreadings is examined. The results show that for continuous non-Gaussian data,the PPAN model performs within the determined optimal ranges and close to thelower bound.

Privacy-Preserving Adversarial Network (PPAN) for Continuous non-Gaussian Attributes