mlsanityData to 7 Oct 2026

Considerations on the Theory of Training Models with Differential Privacy

arXiv 2303.04676 ↗First posted 8 Mar 2023cs.LG cs.CRcited by 2

Not on the map. Why?

Abstract (arXiv)

In federated learning collaborative learning takes place by a set of clients who each want to remain in control of how their local training data is used, in particular, how can each client's local training data remain private? Differential privacy is one method to limit privacy leakage. We provide a general overview of its framework and provable properties, adopt the more recent hypothesis based definition called Gaussian DP or f-DP, and discuss Differentially Private Stochastic Gradient Descent (DP-SGD). We stay at a meta level and attempt intuitive explanations and insights textitin this book chapter.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 33 of its 58 references that are in the map. First posted on arXiv 8 Mar 2023.

Builds on

33 of 58 references.

References · 33

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  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. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  7. 2019Deep Leakage from Gradientscited by 1,004
  8. 2019Towards Federated Learning at Scale: System Designcited by 826
  9. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  10. 2017Renyi Differential Privacycited by 643
  11. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  12. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
21 more
  1. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  2. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
  3. 2018Scalable Private Learning with PATEcited by 266
  4. 2019Asynchronous Federated Optimizationcited by 264
  5. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  6. 2020Threats to Federated Learning: A Surveycited by 171
  7. 2017Asynchronous Decentralized Parallel Stochastic Gradient Descentcited by 159
  8. 2017Revisiting Distributed Synchronous SGDcited by 142
  9. 2016Concentrated Differential Privacycited by 139
  10. 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
  11. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  12. 2015Asynchronous Parallel Stochastic Gradient for Nonconvex Optimizationcited by 115
  13. 2018SGD and Hogwild! Convergence Without the Bounded Gradients Assumptioncited by 94
  14. 2021Optimal Accounting of Differential Privacy via Characteristic Functioncited by 83
  15. 2019Differentially Private Model Publishing for Deep Learningcited by 69
  16. 2015Perturbed Iterate Analysis for Asynchronous Stochastic Optimizationcited by 67
  17. 2015Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithmscited by 31
  18. 2018New Convergence Aspects of Stochastic Gradient Algorithmscited by 30
  19. 2013Local Privacy, Data Processing Inequalities, and Statistical Minimax Ratescited by 26
  20. 2021F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (Extended Version)cited by 23
  21. 2020Hogwild! over Distributed Local Data Sets with Linearly Increasing Mini-Batch Sizescited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023Protect Your Score: Contact Tracing With Differential Privacy Guaranteescited by 5
  2. 2024DNA: Differentially private Neural Augmentation for contact tracingcited by 0