ICML 2021spotlight44 citations

Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message

Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh, Amer Sinha

Abstract

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.

BibTeX
@InProceedings{pmlr-v139-ghazi21a,
  title = 	 {Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message},
  author =       {Ghazi, Badih and Kumar, Ravi and Manurangsi, Pasin and Pagh, Rasmus and Sinha, Amer},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {3692--3701},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/ghazi21a/ghazi21a.pdf},
  url = 	 {https://proceedings.mlr.press/v139/ghazi21a.html},
  abstract = 	 {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.}
}
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message · ICML 2021