mlsanityData to 14 Oct 2026

Cross-silo Federated Learning with Record-level Personalized Differential Privacy

arXiv 2401.16251 ↗First posted 29 Jan 2024cs.CR cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enhanced by differential privacy has emerged as a popular approach to better safeguard the privacy of client-side data by protecting clients' contributions during the training process. Existing solutions typically assume a uniform privacy budget for all records and provide one-size-fits-all solutions that may not be adequate to meet each record's privacy requirement. In this paper, we explore the uncharted territory of cross-silo FL with record-level personalized differential privacy. We devise a novel framework named textitrPDP-FL, employing a two-stage hybrid sampling scheme with both uniform client-level sampling and non-uniform record-level sampling to accommodate varying privacy requirements. A critical and non-trivial problem is how to determine the ideal per-record sampling probability q given the personalized privacy budget varepsilon. We introduce a versatile solution named textitSimulation-CurveFitting, allowing us to uncover a significant insight into the nonlinear correlation between q and varepsilon and derive an elegant mathematical model to tackle the problem. Our evaluation demonstrates that our solution can provide significant performance gains over the baselines that do not consider personalized privacy preservation.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 38 of its 67 references that are in the map. First posted on arXiv 29 Jan 2024.

Builds on

38 of 67 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2019Advances and Open Problems in Federated Learningcited by 3,046
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  7. 2016Deep Learning with Differential Privacycited by 2,728
  8. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  9. 2019Deep Leakage from Gradientscited by 1,021
  10. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 722
  11. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  12. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
26 more
  1. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  2. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 383
  3. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  4. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  5. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  6. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 242
  7. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 236
  8. 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 204
  9. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  10. 2016Concentrated Differential Privacycited by 144
  11. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
  12. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 123
  13. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  14. 2020Individual Privacy Accounting via a Renyi Filtercited by 59
  15. 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
  16. 2016Privacy Odometers and Filters: Pay-as-you-Go Compositioncited by 33
  17. 2021Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Lossescited by 30
  18. 2022Private Non-Convex Federated Learning Without a Trusted Servercited by 26
  19. 2023Have it your way: Individualized Privacy Assignment for DP-SGDcited by 21
  20. 2023Practical Differentially Private and Byzantine-resilient Federated Learningcited by 18
  21. 2022Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guaranteescited by 10
  22. 2022Differentially Private Vertical Federated Clusteringcited by 10
  23. 2023DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Releasecited by 10
  24. 2022Federated Boosted Decision Trees with Differential Privacycited by 9
  25. 2023ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacycited by 9
  26. 2023Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Modelcited by 4

Built on by

Cited by year (2026 to 14 Oct)

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

9 papers.

  1. 2025FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Healthcited by 5
  2. 2025Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacycited by 1
  3. 2026United We Defend: Collaborative Membership Inference Defenses in Federated Learningcited by 1
  4. 2026DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Modelscited by 1
  5. 2024Fluent: Round-efficient Secure Aggregation for Private Federated Learningcited by 0
  6. 2024Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Securitycited by 0
  7. 2025FedSGT: Exact Federated Unlearning via Sequential Group-based Trainingcited by 0
  8. 2026Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregationcited by 0
  9. 2026FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgettingcited by 0