EUVIMEDSkopri EUVIMED
Open access · CC BY-NC-ND 4.0

Discrete Gaussian for Differential Privacy

Clement Canonne, Gautam Kamath, Thomas Steinke

Journal of Privacy and Confidentiality · 2022-07-29 · 12 (1)

DOI: 10.29012/jpc.784 ↗

At a glance

Journal article in Journal of Privacy and Confidentiality, published online on 2022-07-29. Written by Clement Canonne and 2 co-authors. Cited 66 times so far (Crossref). The full text is freely available (open access, CC BY-NC-ND 4.0).

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

A key tool for building differentially private systems is adding Gaussian noise to the output of a function evaluated on a sensitive dataset. Unfortunately, using a continuous distribution presents several practical challenges. First and foremost, finite computers cannot exactly represent samples from continuous distributions, and previous work has demonstrated that seemingly innocuous numerical errors can entirely destroy privacy. Moreover, when the underlying data is itself discrete (e.g., population counts), adding continuous noise makes the result less interpretable. With these shortcomings in mind, we introduce and analyze the discrete Gaussian in the context of differential privacy. Specifically, we theoretically and experimentally show that adding discrete Gaussian noise provides essentially the same privacy and accuracy guarantees as the addition of continuous Gaussian noise. We also present an simple and efficient algorithm for exact sampling from this distribution. This demonstrates its applicability for privately answering counting queries, or more generally, low-sensitivity integer-valued queries.

Cite

APA

Canonne, C., Kamath, G., & Steinke, T. (2022). Discrete Gaussian for Differential Privacy. Journal of Privacy and Confidentiality, 12(1). https://doi.org/10.29012/jpc.784

Vancouver

Canonne C, Kamath G, Steinke T. Discrete Gaussian for Differential Privacy. Journal of Privacy and Confidentiality. 2022;12(1). doi:10.29012/jpc.784

BibTeX
@article{Canonne2022,
  author = {Canonne, Clement and Kamath, Gautam and Steinke, Thomas},
  title = {Discrete Gaussian for Differential Privacy},
  journal = {Journal of Privacy and Confidentiality},
  year = {2022},
  volume = {12},
  number = {1},
  doi = {10.29012/jpc.784}
}
Start for free →