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

arXiv:2307.06708v2 Announce Type: replace
Abstract: 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. …

abstract arxiv budget community cs.cl cs.cr data data sharing differential differential privacy framework interpretation key nlp nlp systems privacy risks systems the key training type