mlsanityData to 7 Oct 2026

Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communication

arXiv 2102.04737 ↗First posted 9 Feb 2021cs.LG cs.CR cs.DCcited by 38

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) allows to train a massive amount of data privately due to its decentralized structure. Stochastic gradient descent (SGD) is commonly used for FL due to its good empirical performance, but sensitive user information can still be inferred from weight updates shared during FL iterations. We consider Gaussian mechanisms to preserve local differential privacy (LDP) of user data in the FL model with SGD. The trade-offs between user privacy, global utility, and transmission rate are proved by defining appropriate metrics for FL with LDP. Compared to existing results, the query sensitivity used in LDP is defined as a variable and a tighter privacy accounting method is applied. The proposed utility bound allows heterogeneous parameters over all users. Our bounds characterize how much utility decreases and transmission rate increases if a stronger privacy regime is targeted. Furthermore, given a target privacy level, our results guarantee a significantly larger utility and a smaller transmission rate as compared to existing privacy accounting methods.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 12 of its 23 references that are in the map. First posted on arXiv 9 Feb 2021.

Builds on

12 of 23 references.

References · 12

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  4. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  5. 2013The Composition Theorem for Differential Privacycited by 290
  6. 2017Collecting Telemetry Data Privatelycited by 147
  7. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  8. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 103
  9. 2020LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacycited by 63
  10. 2020Wireless Federated Learning with Local Differential Privacycited by 50
  11. 2020FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selectioncited by 35
  12. 2020A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergencescited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 8; 2023: 9; 2024: 11; 2025: 5; 2026: 1.

38 papers.

Sort:

By area:

  1. 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
  2. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 34
  3. 2022One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacycited by 26
  4. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  5. 2021FedLess: Secure and Scalable Federated Learning Using Serverless Computingcited by 13
  6. 2023Securing Distributed SGD against Gradient Leakage Threatscited by 13
  7. 2024The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscapecited by 13
  8. 2022Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-Ray Datacited by 8
  9. 2021FLSys: Toward an Open Ecosystem for Federated Learning Mobile Appscited by 6
  10. 2023Client-Level Differential Privacy via Adaptive Intermediary in Federated Medical Imagingcited by 6
  11. 2024Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-offcited by 6
  12. 2021Federated Learning with Heterogeneous Differential Privacycited by 5
26 more
  1. 2024Mitigating Privacy Risk in Membership Inference by Convex-Concave Losscited by 5
  2. 2023Privacy Preservation in Artificial Intelligence and Extended Reality (AI-XR) Metaverses: A Surveycited by 3
  3. 2022FedLesScan: Mitigating Stragglers in Serverless Federated Learningcited by 2
  4. 2023Personalized DP-SGD using Sampling Mechanismscited by 2
  5. 2024Age Aware Scheduling for Differentially-Private Federated Learningcited by 2
  6. 2025Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learningcited by 2
  7. 2021The More, the Better? A Study on Collaborative Machine Learning for DGA Detectioncited by 1
  8. 2022A New Dimensionality Reduction Method Based on Hensel's Compression for Privacy Protection in Federated Learningcited by 1
  9. 2022Matching Pursuit Based Scheduling for Over-the-Air Federated Learningcited by 1
  10. 2022Optimal Privacy Preserving for Federated Learning in Mobile Edge Computingcited by 1
  11. 2023Balancing Privacy and Performance for Private Federated Learning Algorithmscited by 1
  12. 2023Differentially Private Wireless Federated Learning Using Orthogonal Sequencescited by 1
  13. 2023Federated Learning with Reduced Information Leakage and Computationcited by 1
  14. 2024Exposing the Vulnerability of Decentralized Learning to Membership Inference Attacks Through the Lens of Graph Mixingcited by 1
  15. 2025PAUSE: Low-Latency and Privacy-Aware Active User Selection for Federated Learningcited by 1
  16. 2026Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysiscited by 1
  17. 2023Exploring the Benefits of Differentially Private Pre-training and Parameter-Efficient Fine-tuning for Table Transformerscited by 0
  18. 2024Data Quality in Edge Machine Learning: A State-of-the-Art Surveycited by 0
  19. 2024QBI: Quantile-Based Bias Initialization for Efficient Private Data Reconstruction in Federated Learningcited by 0
  20. 2024Federated Hypergraph Learning with Local Differential Privacy: Toward Privacy-Aware Hypergraph Structure Completioncited by 0
  21. 2024Convergent Differential Privacy Analysis for General Federated Learningcited by 0
  22. 2024Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computingcited by 0
  23. 2024Privacy-Preserving Federated Learning via Homomorphic Adversarial Networkscited by 0
  24. 2025FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learningcited by 0
  25. 2025Privacy-Preserving Quantized Federated Learning with Diverse Precisioncited by 0
  26. 2025Poison to Detect: Detection of Targeted Overfitting in Federated Learningcited by 0