Standard
Differentially Private Aggregation in the Shuffle Model : Almost Central Accuracy in Almost a Single Message. / Ghazi, Badih; Kumar, Ravi; Manurangsi, Pasin; Pagh, Rasmus; Sinha, Amer.
Proceedings of the 38 th International Conference on Machine Learning. ed. / M Meila; T Zhang. PMLR, 2021. p. 3692-3701 (Proceedings of Machine Learning Research, Vol. 139).
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
Ghazi, B, Kumar, R, Manurangsi, P
, Pagh, R & Sinha, A 2021,
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message. in M Meila & T Zhang (eds),
Proceedings of the 38 th International Conference on Machine Learning. PMLR, Proceedings of Machine Learning Research, vol. 139, pp. 3692-3701, 38th International Conference on Machine Learning (ICML), Virtual,
18/07/2021. <
https://proceedings.mlr.press/v139/>
APA
Ghazi, B., Kumar, R., Manurangsi, P.
, Pagh, R., & Sinha, A. (2021).
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message. In M. Meila, & T. Zhang (Eds.),
Proceedings of the 38 th International Conference on Machine Learning (pp. 3692-3701). PMLR. Proceedings of Machine Learning Research Vol. 139
https://proceedings.mlr.press/v139/Vancouver
Ghazi B, Kumar R, Manurangsi P, Pagh R, Sinha A. Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message. In Meila M, Zhang T, editors, Proceedings of the 38 th International Conference on Machine Learning. PMLR. 2021. p. 3692-3701. (Proceedings of Machine Learning Research, Vol. 139).
Author
Ghazi, Badih ; Kumar, Ravi ; Manurangsi, Pasin ; Pagh, Rasmus ; Sinha, Amer. / Differentially Private Aggregation in the Shuffle Model : Almost Central Accuracy in Almost a Single Message. Proceedings of the 38 th International Conference on Machine Learning. editor / M Meila ; T Zhang. PMLR, 2021. pp. 3692-3701 (Proceedings of Machine Learning Research, Vol. 139).
Bibtex
@inproceedings{29340b4d5f694709b33603b32d9ae8cb,
title = "Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message",
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.",
keywords = "NOISE",
author = "Badih Ghazi and Ravi Kumar and Pasin Manurangsi and Rasmus Pagh and Amer Sinha",
year = "2021",
language = "English",
series = "Proceedings of Machine Learning Research",
pages = "3692--3701",
editor = "M Meila and T Zhang",
booktitle = "Proceedings of the 38 th International Conference on Machine Learning",
publisher = "PMLR",
note = "38th International Conference on Machine Learning (ICML) ; Conference date: 18-07-2021 Through 24-07-2021",
}
RIS
TY - GEN
T1 - Differentially Private Aggregation in the Shuffle Model
T2 - 38th International Conference on Machine Learning (ICML)
AU - Ghazi, Badih
AU - Kumar, Ravi
AU - Manurangsi, Pasin
AU - Pagh, Rasmus
AU - Sinha, Amer
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - NOISE
M3 - Article in proceedings
T3 - Proceedings of Machine Learning Research
SP - 3692
EP - 3701
BT - Proceedings of the 38 th International Conference on Machine Learning
A2 - Meila, M
A2 - Zhang, T
PB - PMLR
Y2 - 18 July 2021 through 24 July 2021
ER -
