mlsanityData to 14 Oct 2026

ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy

arXiv 2308.12210 ↗First posted 23 Aug 2023cs.LG cs.CRcited by 9

Not on the map. Why?

Abstract (arXiv)

Differentially Private Federated Learning (DP-FL) has garnered attention as a collaborative machine learning approach that ensures formal privacy. Most DP-FL approaches ensure DP at the record-level within each silo for cross-silo FL. However, a single user's data may extend across multiple silos, and the desired user-level DP guarantee for such a setting remains unknown. In this study, we present Uldp-FL, a novel FL framework designed to guarantee user-level DP in cross-silo FL where a single user's data may belong to multiple silos. Our proposed algorithm directly ensures user-level DP through per-user weighted clipping, departing from group-privacy approaches. We provide a theoretical analysis of the algorithm's privacy and utility. Additionally, we enhance the utility of the proposed algorithm with an enhanced weighting strategy based on user record distribution and design a novel private protocol that ensures no additional information is revealed to the silos and the server. Experiments on real-world datasets show substantial improvements in our methods in privacy-utility trade-offs under user-level DP compared to baseline methods. To the best of our knowledge, our work is the first FL framework that effectively provides user-level DP in the general cross-silo FL setting.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 35 of its 65 references that are in the map. First posted on arXiv 23 Aug 2023.

Builds on

35 of 65 references.

References · 35

  1. 2019Advances and Open Problems in Federated Learningcited by 3,046
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2020Adaptive Federated Optimizationcited by 1,046
  4. 2017Renyi Differential Privacycited by 650
  5. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  6. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  7. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 383
  8. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  9. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 236
  10. 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 204
  11. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 193
  12. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
23 more
  1. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
  2. 2019Federated Learning for Emoji Prediction in a Mobile Keyboardcited by 118
  3. 2018Distributed Differential Privacy via Shufflingcited by 115
  4. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  5. 2019Hypothesis Testing Interpretations and Renyi Differential Privacycited by 85
  6. 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 85
  7. 2018A General Approach to Adding Differential Privacy to Iterative Training Procedurescited by 84
  8. 2021Learning with User-Level Privacycited by 72
  9. 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 69
  10. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 68
  11. 2020Learning discrete distributions: user vs item-level privacycited by 41
  12. 2020Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluationcited by 39
  13. 2021Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learningcited by 39
  14. 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
  15. 2021Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Lossescited by 30
  16. 2019Differentially Private SQL with Bounded User Contributioncited by 27
  17. 2022Private Non-Convex Federated Learning Without a Trusted Servercited by 26
  18. 2020FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learningcited by 6
  19. 2022Network Shuffling: Privacy Amplification via Random Walkscited by 6
  20. 2019Capacity Bounded Differential Privacycited by 5
  21. 2020Private Weighted Sum Aggregationcited by 4
  22. 2021Preventing Manipulation Attack in Local Differential Privacy using Verifiable Randomization Mechanismcited by 4
  23. 2022OLIVE: Oblivious Federated Learning on Trusted Execution Environment against the risk of sparsificationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 3.

9 papers.

  1. 2024Fine-Tuning Large Language Models with User-Level Differential Privacycited by 29
  2. 2024Cross-silo Federated Learning with Record-level Personalized Differential Privacycited by 9
  3. 2025FuSeFL: Fully Secure and Scalable Federated Learningcited by 2
  4. 2026Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Datacited by 1
  5. 2025An Empirical Study of the Impact of Federated Learning on Machine Learning Model Accuracycited by 0
  6. 2025On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacycited by 0
  7. 2025Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participationcited by 0
  8. 2026Matrix Factorization for Practical Continual Mean Estimation Under User-Level Differential Privacycited by 0
  9. 2026An Adaptive Differentially Private Federated Learning Frameworkcited by 0