Data to 14 Oct 2026

Federated Learning with Bayesian Differential Privacy

arXiv 1911.10071 ↗First posted 22 Nov 2019cs.LG cs.CR cs.DCcited by 60

Not on the map. Why?

Abstract (arXiv)

We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy loss bounds. We adapt the Bayesian privacy accounting method to the federated setting and suggest multiple improvements for more efficient privacy budgeting at different levels. Our experiments show significant advantage over the state-of-the-art differential privacy bounds for federated learning on image classification tasks, including a medical application, bringing the privacy budget below 1 at the client level, and below 0.1 at the instance level. Lower amounts of noise also benefit the model accuracy and reduce the number of communication rounds.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 17; 2023: 12; 2024: 7; 2025: 9; 2026: 2.

60 papers.

Sort:

By area:

2022FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learningcited by 91
2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 69
2022FederatedScope: A Flexible Federated Learning Platform for Heterogeneitycited by 53
2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
2021FedCV: A Federated Learning Framework for Diverse Computer Vision Taskscited by 32
2023Conformal Prediction for Federated Uncertainty Quantification Under Label Shiftcited by 29
2022On the Impossible Safety of Large AI Modelscited by 28
2022A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learningcited by 27
2021Low-Latency Federated Learning over Wireless Channels with Differential Privacycited by 25
2022FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneitycited by 25
2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24

38 more

2021Privacy Amplification for Federated Learning via User Sampling and Wireless Aggregationcited by 22
2023Bayesian Federated Learning: A Surveycited by 22
2023Federated Learning for Computer Visioncited by 22
2022FedCross: Towards Accurate Federated Learning via Multi-Model Cross-Aggregationcited by 21
2021Generative Adversarial Networks: A Survey Towards Private and Secure Applicationscited by 15
2021A Graph Federated Architecture with Privacy Preserving Learningcited by 10
2023DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learningcited by 10
2023Tunable Soft Prompts are Messengers in Federated Learningcited by 10
2021Federated Learning Meets Fairness and Differential Privacycited by 9
2021Efficient and Reliable Overlay Networks for Decentralized Federated Learningcited by 9
2021A Federated Data-Driven Evolutionary Algorithmcited by 8
2022Federated Stochastic Primal-dual Learning with Differential Privacycited by 5
2022A review of Federated Learning in Intrusion Detection Systems for IoTcited by 4
2023PriPrune: Quantifying and Preserving Privacy in Pruned Federated Learningcited by 4
2025From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challengescited by 4
2022FedComm: Federated Learning as a Medium for Covert Communicationcited by 3
2022LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximationcited by 3
2022Differentially Private Federated Combinatorial Bandits with Constraintscited by 3
2022FedMCSA: Personalized Federated Learning via Model Components Self-Attentioncited by 3
2023Enforcing Privacy in Distributed Learning with Performance Guaranteescited by 3
2024Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectivescited by 3
2024An Adaptive Differential Privacy Method Based on Federated Learningcited by 3
2021A Vertical Federated Learning Method For Multi-Institutional Credit Scoring: MICScited by 2
2021Robust Convergence in Federated Learning through Label-wise Clusteringcited by 2
2022A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observationscited by 2
2023Privacy Preserving Bayesian Federated Learning in Heterogeneous Settingscited by 2
2026FSL-BDP: Federated Survival Learning with Bayesian Differential Privacy for Credit Risk Modelingcited by 2
2021Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacycited by 1
2022Privatized Graph Federated Learningcited by 1
2022Mixed Precision Quantization to Tackle Gradient Leakage Attacks in Federated Learningcited by 1
2023FedBlockHealth: A Synergistic Approach to Privacy and Security in IoT-Enabled Healthcare through Federated Learning and Blockchaincited by 1
2023Federated Learning with Reduced Information Leakage and Computationcited by 1
2023Decentralized Personalized Online Federated Learningcited by 1
2024Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergencecited by 1
2024Task Diversity in Bayesian Federated Learning: Simultaneous Processing of Classification and Regressioncited by 1
2025Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregationcited by 1
2025First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptionscited by 1
2022Decentralized Matrix Factorization with Heterogeneous Differential Privacycited by 0

50 most cited of 60 All 60 (JSON)