The Discrete Gaussian for Differential Privacy
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 f...
Guardat en:
| Autors principals: | , , |
|---|---|
| Format: | Artigo |
| Idioma: | Inglês |
| Publicat: |
Labor Dynamics Institute
2022-07-01
|
| Col·lecció: | The Journal of Privacy and Confidentiality |
| Matèries: | |
| Accés en línia: | http://www.journalprivacyconfidentiality.org/index.php/jpc/article/view/784 |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|