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...
I tiakina i:
| Ngā kaituhi matua: | , , |
|---|---|
| Hōputu: | Artigo |
| Reo: | Inglês |
| I whakaputaina: |
Labor Dynamics Institute
2022-07-01
|
| Rangatū: | The Journal of Privacy and Confidentiality |
| Ngā marau: | |
| Urunga tuihono: | http://www.journalprivacyconfidentiality.org/index.php/jpc/article/view/784 |
| Ngā Tūtohu: |
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
|