mlsanityData to 14 Oct 2026

Federated Learning with Differential Privacy: Algorithms and Performance Analysis

arXiv 1911.00222 ↗First posted 1 Nov 2019cs.LG cs.NIcited by 536

Not on the map. Why?

Abstract (arXiv)

In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noises are added to the parameters at the clients side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting different variances of artificial noises. Then we develop a theoretical convergence bound of the loss function of the trained FL model in the NbAFL. Specifically, the theoretical bound reveals the following three key properties: 1) There is a tradeoff between the convergence performance and privacy protection levels, i.e., a better convergence performance leads to a lower protection level; 2) Given a fixed privacy protection level, increasing the number N of overall clients participating in FL can improve the convergence performance; 3) There is an optimal number of maximum aggregation times (communication rounds) in terms of convergence performance for a given protection level. Furthermore, we propose a K-random scheduling strategy, where K (1<K<N) clients are randomly selected from the N overall clients to participate in each aggregation. We also develop the corresponding convergence bound of the loss function in this case and the K-random scheduling strategy can also retain the above three properties. Moreover, we find that there is an optimal K that achieves the best convergence performance at a fixed privacy level. Evaluations demonstrate that our theoretical results are consistent with simulations, thereby facilitating the designs on various privacy-preserving FL algorithms with different tradeoff requirements on convergence performance and privacy levels.

Key facts. Cited by 536 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 72; 2022: 86; 2023: 128; 2024: 108; 2025: 97; 2026: 45.

536 papers.

Sort:

By area:

  1. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  2. 2021Trustworthy AI: From Principles to Practicescited by 207
  3. 2021Federated Learning for Smart Healthcare: A Surveycited by 184
  4. 2023Large Language Models in Law: A Surveycited by 128
  5. 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 128
  6. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 127
  7. 2021Trustworthy AI: A Computational Perspectivecited by 93
  8. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  9. 2022Federated Learning Enables Big Data for Rare Cancer Boundary Detectioncited by 84
  10. 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
  11. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  12. 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 69
38 more
  1. 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 66
  2. 2022Black-box Dataset Ownership Verification via Backdoor Watermarkingcited by 65
  3. 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
  4. 2024AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networkscited by 64
  5. 2024SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 62
  6. 2021Distributed Deep Learning in Open Collaborationscited by 58
  7. 2021Personalized Federated Learning through Local Memorizationcited by 57
  8. 2021Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocationcited by 56
  9. 2021Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edgecited by 56
  10. 2022Vertical Federated Learning: Challenges, Methodologies and Experimentscited by 55
  11. 2022Personalized Subgraph Federated Learningcited by 54
  12. 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
  13. 2022FederatedScope: A Flexible Federated Learning Platform for Heterogeneitycited by 53
  14. 2023FedMultimodal: A Benchmark For Multimodal Federated Learningcited by 51
  15. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  16. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  17. 2022pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learningcited by 44
  18. 2021Federated Learning Meets Natural Language Processing: A Surveycited by 43
  19. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 41
  20. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  21. 2023Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learningcited by 41
  22. 2022A Survey on Gradient Inversion: Attacks, Defenses and Future Directionscited by 40
  23. 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
  24. 2021Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communicationcited by 39
  25. 2021Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learningcited by 39
  26. 2021FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learningcited by 39
  27. 2021FedIPR: Ownership Verification for Federated Deep Neural Network Modelscited by 36
  28. 2021Non-IID data and Continual Learning processes in Federated Learning: A long road aheadcited by 36
  29. 2023LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulationcited by 36
  30. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 35
  31. 2021Differentially Private Federated Bayesian Optimization with Distributed Explorationcited by 32
  32. 2021Federated Neural Collaborative Filteringcited by 30
  33. 2021Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Lossescited by 30
  34. 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
  35. 2023Conformal Prediction for Federated Uncertainty Quantification Under Label Shiftcited by 29
  36. 2023Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learningcited by 29
  37. 2022FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulationscited by 27
  38. 2021FedFace: Collaborative Learning of Face Recognition Modelcited by 26

50 most cited of 536 All 536 (JSON)