mlsanityData to 7 Oct 2026

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

arXiv 2109.13158 ↗First posted 27 Sep 2021cs.CR cs.DScited by 18

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Sep 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 3; 2024: 4; 2025: 2; 2026: 2.

18 papers.

Sort:

  1. 2022Private Non-Convex Federated Learning Without a Trusted Servercited by 26
  2. 2022Regression with Label Differential Privacycited by 14
  3. 2021User-Level Private Learning via Correlated Samplingcited by 9
  4. 2022Network Shuffling: Privacy Amplification via Random Walkscited by 6
  5. 2023Samplable Anonymous Aggregation for Private Federated Data Analysiscited by 6
  6. 2023Optimal Unbiased Randomizers for Regression with Label Differential Privacycited by 6
  7. 2022Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summationcited by 5
  8. 2024Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messagescited by 5
  9. 2022Transfer Learning In Differential Privacy's Hybrid-Modelcited by 3
  10. 2023Multi-Message Shuffled Privacy in Federated Learningcited by 2
  11. 2024Making Old Things New: A Unified Algorithm for Differentially Private Clusteringcited by 1
  12. 2024Beyond Statistical Estimation: Differentially Private Individual Computation via Shufflingcited by 1
6 more
  1. 2025Learning from End User Data with Shuffled Differential Privacy over Kernel Densitiescited by 1
  2. 2025PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectorscited by 1
  3. 2021Infinitely Divisible Noise in the Low Privacy Regimecited by 0
  4. 2024Differential Privacy on Trust Graphscited by 0
  5. 2026Shuffle and Joint Differential Privacy for Generalized Linear Contextual Banditscited by 0
  6. 2026Shuffling-Aware Optimization for Private Vector Mean Estimationcited by 0