English

Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy

Cryptography and Security 2026-03-25 v1 Computation and Language

Abstract

The growing use of large language models has increased interest in sharing textual data in a privacy-preserving manner. One prominent line of work addresses this challenge through text rewriting under Local Differential Privacy (LDP), where input texts are locally obfuscated before release with formal privacy guarantees. These guarantees are typically expressed by a parameter ε\varepsilon that upper bounds the worst-case privacy loss. However, nominal ε\varepsilon values are often difficult to interpret and compare across mechanisms. In this work, we investigate how to empirically calibrate across text rewriting mechanisms under LDP. We propose TeDA, which formulates calibration via a hypothesis-testing framework that instantiates text distinguishability audits in both surface and embedding spaces, enabling empirical assessment of indistinguishability from privatized texts. Applying this calibration to several representative mechanisms, we demonstrate that similar nominal ε\varepsilon bounds can imply very different levels of distinguishability. Empirical calibration thus provides a more comparable footing for evaluating privacy-utility trade-offs, as well as a practical tool for mechanism comparison and analysis in real-world LDP text rewriting deployments.

Keywords

Cite

@article{arxiv.2603.22968,
  title  = {Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy},
  author = {Weijun Li and Arnaud Grivet Sébert and Qiongkai Xu and Annabelle McIver and Mark Dras},
  journal= {arXiv preprint arXiv:2603.22968},
  year   = {2026}
}

Comments

22 pages, 11 figures, 5 tables