mlsanityData to 7 Oct 2026

Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning

arXiv 2406.03519 ↗First posted 5 Jun 2024cs.LG cs.CR cs.DCcited by 9

Not on the map. Why?

Abstract (arXiv)

High utility and rigorous data privacy are of the main goals of a federated learning (FL) system, which learns a model from the data distributed among some clients. The latter has been tried to achieve by using differential privacy in FL (DPFL). There is often heterogeneity in clients privacy requirements, and existing DPFL works either assume uniform privacy requirements for clients or are not applicable when server is not fully trusted (our setting). Furthermore, there is often heterogeneity in batch and/or dataset size of clients, which as shown, results in extra variation in the DP noise level across clients model updates. With these sources of heterogeneity, straightforward aggregation strategies, e.g., assigning clients aggregation weights proportional to their privacy parameters will lead to lower utility. We propose Robust-HDP, which efficiently estimates the true noise level in clients model updates and reduces the noise-level in the aggregated model updates considerably. Robust-HDP improves utility and convergence speed, while being safe to the clients that may maliciously send falsified privacy parameter to server. Extensive experimental results on multiple datasets and our theoretical analysis confirm the effectiveness of Robust-HDP. Our code can be found here.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 5 Jun 2024.

Builds on

36 of 51 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2019Deep Leakage from Gradientscited by 1,004
  6. 2013Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programmingcited by 716
  7. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  8. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  9. 2020Federated Learning with Matched Averagingcited by 564
  10. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
  11. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  12. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
24 more
  1. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  2. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  3. 2018Gradient Descent Happens in a Tiny Subspacecited by 208
  4. 2020A Survey of Privacy Attacks in Machine Learningcited by 143
  5. 2020Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identificationcited by 88
  6. 2020Local Differential Privacy based Federated Learning for Internet of Thingscited by 74
  7. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  8. 2019Differentially Private Model Publishing for Deep Learningcited by 69
  9. 2021Selective Differential Privacy for Language Modelingcited by 61
  10. 2020Model-sharing Games: Analyzing Federated Learning Under Voluntary Participationcited by 60
  11. 2022Differential Privacy and Fairness in Decisions and Learning Tasks: A Surveycited by 47
  12. 2022Mechanisms that Incentivize Data Sharing in Federated Learningcited by 38
  13. 2015Heterogeneous Differential Privacycited by 30
  14. 2020FLAME: Differentially Private Federated Learning in the Shuffle Modelcited by 27
  15. 2022Optimal and Differentially Private Data Acquisition: Central and Local Mechanismscited by 22
  16. 2023Have it your way: Individualized Privacy Assignment for DP-SGDcited by 21
  17. 2022Proportional Fairness in Federated Learningcited by 20
  18. 2022Individual Privacy Accounting for Differentially Private Stochastic Gradient Descentcited by 20
  19. 2023Provably Personalized and Robust Federated Learningcited by 11
  20. 2017One-sided Differential Privacycited by 10
  21. 2023The Fair Value of Data Under Heterogeneous Privacy Constraints in Federated Learningcited by 5
  22. 2023Trade-Offs Between Fairness and Privacy in Language Modelingcited by 4
  23. 2024Differentially Private Clustered Federated Learningcited by 4
  24. 2023Personalized DP-SGD using Sampling Mechanismscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 5.

9 papers.

  1. 2025Differentially Private Federated Learning With Time-Adaptive Privacy Spendingcited by 5
  2. 2024On Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Stepscited by 1
  3. 2025Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacycited by 1
  4. 2025Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participationcited by 0
  5. 2026An Adaptive Differentially Private Federated Learning Frameworkcited by 0
  6. 2026Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregationcited by 0
  7. 2026Secure and Privacy-Preserving Vertical Federated Learningcited by 0
  8. 2026An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learningcited by 0
  9. 2026Feature Suppression and Differential Privacy for Residential Traffic Classification: A Two-Home Federated Studycited by 0