Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
By Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh, Amer Sinha. 2021
45 citations recorded by the source corpus.
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 the central model, while each user only sends $1 + o(1)$ short messages in expectation.
Subfields: Artificial Intelligence
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
- Pasin Manurangsi
- Badih Ghazi
- Ravi Kumar
- Rasmus Pagh
- Alisa Chang
- Albert Cheu
- David P. Woodruff
- Victor Balcer
Citations in the corpus
- Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead (2020, background): “Most relevant to us are our follow-up work (Ghazi et al., 2021) which”
- Locally Private k-Means in One Round (2021, methodology): “…shuffle DP model includes work on aggregation (Balle et al., 2019; Ghazi et al., 2020d; Balle et al., 2020; Ghazi et al., 2021b), histograms and heavy hitters (Ghazi et al., 2021a; Balcer and Cheu, 2020; Ghazi et al., 2020a,c), and counting distinct elements (Balcer et al., 2021; Chen et al., 2021).”