Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Fulltext
Forlagets udgivne version, 673 KB, PDF-dokument
The shuffle model of differential privacy has attracted attention in the literature due to it being a middle ground between the well-studied central and local models. In this work, we study the problem of summing (aggregating) real numbers or integers, a basic primitive in numerous machine learning tasks, in the shuffle model. We give a protocol achieving error arbitrarily close to that of the (Discrete) Laplace mechanism in central differential privacy, while each user only sends 1 + o(1) short messages in expectation.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the 38 th International Conference on Machine Learning |
Redaktører | M Meila, T Zhang |
Forlag | PMLR |
Publikationsdato | 2021 |
Sider | 3692-3701 |
Status | Udgivet - 2021 |
Begivenhed | 38th International Conference on Machine Learning (ICML) - Virtual Varighed: 18 jul. 2021 → 24 jul. 2021 |
Konference
Konference | 38th International Conference on Machine Learning (ICML) |
---|---|
By | Virtual |
Periode | 18/07/2021 → 24/07/2021 |
Navn | Proceedings of Machine Learning Research |
---|---|
Vol/bind | 139 |
ISSN | 2640-3498 |
Links
- https://proceedings.mlr.press/v139/
Forlagets udgivne version
ID: 301135973