The power of synergy in differential privacy: Combining a small curator with local randomizers
By Amos Beimel, Aleksandra Korolova, Kobbi Nissim, Or Sheffet, Uri Stemmer. 2019
16 citations recorded by the source corpus.
Motivated by the desire to bridge the utility gap between local and trusted curator models of differential privacy for practical applications, we initiate the theoretical study of a hybrid model introduced by "Blender" [Avent et al.,\ USENIX Security '17], in which differentially private protocols of n agents that work in the local-model are assisted by a differentially private curator that has access to the data of m additional users. We focus on the regime where m << n and study the new capabilities of this (m,n)-hybrid model. We show that, despite the fact that the hybrid model adds no significant new capabilities for the basic task of simple hypothesis-testing, there are many other tasks (under a wide range of parameters) that can be solved in the hybrid model yet cannot be solved either by the curator or by the local-users separately. Moreover, we exhibit additional tasks where at least one round of interaction between the curator and the local-users is necessary -- namely, no hybrid model protocol without such interaction can solve these tasks. Taken together, our results show that the combination of the local model with a small curator can become part of a promising toolkit for designing and implementing differential privacy.
Subfields: Artificial Intelligence, Sociology and Political Science, Privacy & Security
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Martin Jaggi
- Qiang Yang
- Jakub Konecný
- Peter Kairouz
- Peter Richtárik
- Ananda Theertha Suresh
- Jianyu Wang
- Sebastian U. Stich
In Sociology and Political Science
- Aurélien Bellet
- Peter Kairouz
- Rasmus Pagh
- Aleksandra Korolova
- Justin Hsu
- Badih Ghazi
- Salim el Rouayheb
- Rachel Cummings
In Privacy & Security
- Peter Kairouz
- Badih Ghazi
- Rasmus Pagh
- Qiang Yang
- Ziteng Sun
- Adrià Gascón
- H. Brendan McMahan
- Aurélien Bellet
Citations in the corpus
- Advances and Open Problems in Federated Learning (2019, background): “Current work on the hybrid model typically assumes that regardless of the user trust preference, their data comes from the same distribution [39, 141, 53].”
- The Power of the Hybrid Model for Mean Estimation (2018, neutral): “[12].”