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

It has been demonstrated that hidden representation learned by a deep modelcan encode private information of the input, hence can be exploited to recoversuch information with reasonable accuracy. To address this issue, we propose anovel approach called Differentially Private Neural Representation (DPNR) topreserve the privacy of the extracted representation from text. DPNR utilisesDifferential Privacy (DP) to provide a formal privacy guarantee. Further, weshow that masking words via dropout can further enhance privacy. To maintainutility of the learned representation, we integrate DP-noisy representationinto a robust training process to derive a robust target model, which alsohelps for model fairness over various demographic variables. Experimentalresults on benchmark datasets under various parameter settings demonstrate thatDPNR largely reduces privacy leakage without significantly sacrificing the maintask performance.

Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness