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

Although the NLP community has adopted central differential privacy as ago-to framework for privacy-preserving model training or data sharing, thechoice and interpretation of the key parameter, privacy budget $\varepsilon$that governs the strength of privacy protection, remains largely arbitrary. Weargue that determining the $\varepsilon$ value should not be solely in thehands of researchers or system developers, but must also take into account theactual people who share their potentially sensitive data. In other words: Wouldyou share your instant messages for $\varepsilon$ of 10? We address thisresearch gap by designing, implementing, and conducting a behavioral experiment(311 lay participants) to study the behavior of people in uncertaindecision-making situations with respect to privacy-threatening situations.Framing the risk perception in terms of two realistic NLP scenarios and using avignette behavioral study help us determine what $\varepsilon$ thresholds wouldlead lay people to be willing to share sensitive textual data - to ourknowledge, the first study of its kind.

To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?