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

arXiv: https://arxiv.org/abs/2307.06708 · HTML: https://mlsanity.com/paper/2307.06708/

## Key facts

- Cited by 3 papers in the map (data through 7 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 13 Jul 2023.

## Builds on (most cited first, 9 of 9)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Differential Privacy for Text Analytics via Natural Text Sanitization](https://mlsanity.com/paper/2106.01221/) (2021)
- [Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness](https://mlsanity.com/paper/2010.01285/) (2020)
- [Differentially Private Natural Language Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2301.09112/) (2023)
- [Privacy-Preserving Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/2102.09604/) (2021)
- ["I need a better description'': An Investigation Into User Expectations For Differential Privacy](https://mlsanity.com/paper/2110.06452/) (2021)
- [Differential Privacy in Natural Language Processing: The Story So Far](https://mlsanity.com/paper/2208.08140/) (2022)
- [Privacy-Preserving Models for Legal Natural Language Processing](https://mlsanity.com/paper/2211.02956/) (2022)
- [Towards Effective Differential Privacy Communication for Users' Data Sharing Decision and Comprehension](https://mlsanity.com/paper/2003.13922/) (2020)

## Built on by (most cited first, 3 of 3)

- [DP-NMT: Scalable Differentially-Private Machine Translation](https://mlsanity.com/paper/2311.14465/) (2023)
- [Investigating User Perspectives on Differentially Private Text Privatization](https://mlsanity.com/paper/2503.09338/) (2025)
- [DP-IPI: A Hybrid Differential Privacy Text Rewriting Mechanism for Indirect Personal Identifiers in Clinical Texts](https://mlsanity.com/paper/2609.29684/) (2026)

## Abstract (arXiv)

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 share your instant messages for varepsilon of 10? We address this research gap by designing, implementing, and conducting a behavioral experiment (311 lay participants) to study the behavior of people in uncertain decision-making situations with respect to privacy-threatening situations. Framing the risk perception in terms of two realistic NLP scenarios and using a vignette behavioral study help us determine what varepsilon thresholds would lead lay people to be willing to share sensitive textual data - to our knowledge, the first study of its kind.