To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?. (arXiv:2307.06708v1 [cs.CL])

Although the NLP community has adopted central differential privacy as a
go-to framework for privacy-preserving model training or data sharing, the
choice and interpretation of the key parameter, privacy budget $\varepsilon$
that governs the strength of privacy protection, remains largely arbitrary. We
argue that determining the $\varepsilon$ value should not be solely in the
hands of researchers or system developers, but must also take into account the
actual people who share their potentially sensitive data. In other words: Would
you …

accept budget community data data sharing differential privacy framework key model training nlp parameter privacy private protection risks sensitive data share sharing strength systems the key training