mlsanityData to 7 Oct 2026

Federated f-Differential Privacy

arXiv 2102.11158 ↗First posted 22 Feb 2021stat.ML cs.AI cs.CRcited by 29

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information without compromising much on the privacy of their local sensitive data. In this paper, we introduce federated f-differential privacy, a new notion specifically tailored to the federated setting, based on the framework of Gaussian differential privacy. Federated f-differential privacy operates on record level: it provides the privacy guarantee on each individual record of one client's data against adversaries. We then propose a generic private federated learning framework PriFedSync that accommodates a large family of state-of-the-art FL algorithms, which provably achieves federated f-differential privacy. Finally, we empirically demonstrate the trade-off between privacy guarantee and prediction performance for models trained by PriFedSync in computer vision tasks.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 22 of its 41 references that are in the map. First posted on arXiv 22 Feb 2021.

Builds on

22 of 41 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  6. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  7. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  8. 2017Renyi Differential Privacycited by 643
  9. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  10. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  11. 2020Adaptive Personalized Federated Learningcited by 353
  12. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
10 more
  1. 2013The Composition Theorem for Differential Privacycited by 290
  2. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  3. 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
  4. 2016Concentrated Differential Privacycited by 139
  5. 2019Deep Learning with Gaussian Differential Privacycited by 112
  6. 2019Hypothesis Testing Interpretations and Renyi Differential Privacycited by 84
  7. 2019Differentially Private Meta-Learningcited by 40
  8. 2013Private Matchings and Allocationscited by 23
  9. 2020Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansioncited by 13
  10. 2014Jointly Private Convex Programmingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 6; 2024: 10; 2025: 2; 2026: 4.

29 papers.

Sort:

By area:

  1. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  2. 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
  3. 2024Decentralized Federated Learning: A Survey on Security and Privacycited by 25
  4. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  5. 2023z-SignFedAvg: A Unified Stochastic Sign-based Compression for Federated Learningcited by 17
  6. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 14
  7. 2023Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacycited by 13
  8. 2022Adap DP-FL: Differentially Private Federated Learning with Adaptive Noisecited by 12
  9. 2024Trustworthy Distributed AI Systems: Robustness, Privacy, and Governancecited by 12
  10. 2024FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learningcited by 10
  11. 2024Certifiably Byzantine-Robust Federated Conformal Predictioncited by 8
  12. 2024A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theoremcited by 8
17 more
  1. 2023Client-Level Differential Privacy via Adaptive Intermediary in Federated Medical Imagingcited by 6
  2. 2021FedPower: Privacy-Preserving Distributed Eigenspace Estimationcited by 4
  3. 2024Efficient Sparse Least Absolute Deviation Regression with Differential Privacycited by 4
  4. 2021PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacycited by 3
  5. 2023Breaking the Communication-Privacy-Accuracy Tradeoff with f-Differential Privacycited by 3
  6. 2025Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via f-Differential Privacycited by 3
  7. 2026Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modelingcited by 3
  8. 2021Statistical Estimation and Inference via Local SGD in Federated Learningcited by 2
  9. 2021The More, the Better? A Study on Collaborative Machine Learning for DGA Detectioncited by 1
  10. 2023Federated Learning with Reduced Information Leakage and Computationcited by 1
  11. 2024Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergencecited by 1
  12. 2026Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learningcited by 1
  13. 2024Enhancing IoT Security Against DDoS Attacks through Federated Learningcited by 0
  14. 2024Convergent Differential Privacy Analysis for General Federated Learningcited by 0
  15. 2025RiM: Record, Improve and Maintain Physical Well-being using Federated Learningcited by 0
  16. 2026Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregationcited by 0
  17. 2026Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbationcited by 0