mlsanityData to 14 Oct 2026

PAPAYA Federated Analytics Stack: Engineering Privacy, Scalability and Practicality

arXiv 2412.02340 ↗First posted 3 Dec 2024cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Cross-device Federated Analytics (FA) is a distributed computation paradigm designed to answer analytics queries about and derive insights from data held locally on users' devices. On-device computations combined with other privacy and security measures ensure that only minimal data is transmitted off-device, achieving a high standard of data protection. Despite FA's broad relevance, the applicability of existing FA systems is limited by compromised accuracy; lack of flexibility for data analytics; and an inability to scale effectively. In this paper, we describe our approach to combine privacy, scalability, and practicality to build and deploy a system that overcomes these limitations. Our FA system leverages trusted execution environments (TEEs) and optimizes the use of on-device computing resources to facilitate federated data processing across large fleets of devices, while ensuring robust, defensible, and verifiable privacy safeguards. We focus on federated analytics (statistics and monitoring), in contrast to systems for federated learning (ML workloads), and we flag the key differences.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 42 references that are in the map. First posted on arXiv 3 Dec 2024.

Builds on

21 of 42 references.

References · 21

  1. 2019Towards Federated Learning at Scale: System Designcited by 832
  2. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  3. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 272
  4. 2021Papaya: Practical, Private, and Scalable Federated Learningcited by 90
  5. 2021DRIVE: One-bit Distributed Mean Estimationcited by 52
  6. 2022Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributionscited by 52
  7. 2017Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12cited by 43
  8. 2017Prio: Private, Robust, and Scalable Computation of Aggregate Statisticscited by 36
  9. 2019Federated Heavy Hitters Discovery with Differential Privacycited by 32
  10. 2023FLINT: A Platform for Federated Learning Integrationcited by 17
  11. 2020Lightweight Techniques for Private Heavy Hitterscited by 13
  12. 2019Computing Extremely Accurate Quantiles Using t-Digestscited by 10
9 more
  1. 2021Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregationcited by 10
  2. 2019DDSketch: A fast and fully-mergeable quantile sketch with relative-error guaranteescited by 8
  3. 2019Private Protocols for U-Statistics in the Local Model and Beyondcited by 7
  4. 2022Exact Privacy Analysis of the Gaussian Sparse Histogram Mechanismcited by 6
  5. 2023Samplable Anonymous Aggregation for Private Federated Data Analysiscited by 6
  6. 2022Federated Calibration and Evaluation of Binary Classifierscited by 5
  7. 2024Elephants Do Not Forget: Differential Privacy with State Continuity for Privacy Budgetcited by 5
  8. 2021STAR: Secret Sharing for Private Threshold Aggregation Reportingcited by 2
  9. 2023Sketch-Flip-Merge: Mergeable Sketches for Private Distinct Countingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Robust Federated Learning Under Real-World Client Churncited by 0