mlsanityData to 14 Oct 2026

Differential Privacy: What is all the noise about?

arXiv 2205.09453 ↗First posted 19 May 2022cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Differential Privacy (DP) is a formal definition of privacy that provides rigorous guarantees against risks of privacy breaches during data processing. It makes no assumptions about the knowledge or computational power of adversaries, and provides an interpretable, quantifiable and composable formalism. DP has been actively researched during the last 15 years, but it is still hard to master for many Machine Learning (ML)) practitioners. This paper aims to provide an overview of the most important ideas, concepts and uses of DP in ML, with special focus on its intersection with Federated Learning (FL).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 83 references that are in the map. First posted on arXiv 19 May 2022.

Builds on

34 of 83 references.

References · 34

  1. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  4. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  5. 2017Renyi Differential Privacycited by 650
  6. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  7. 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 376
  8. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 348
  9. 2018Scalable Private Learning with PATEcited by 269
  10. 2018Differentially Private Generative Adversarial Networkcited by 235
  11. 2019Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscited by 119
  12. 2020DP-CGAN: Differentially Private Synthetic Data and Label Generationcited by 118
22 more
  1. 2018MaskGAN: Better Text Generation via Filling in the______cited by 89
  2. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  3. 2014Differential Privacy and Machine Learning: a Survey and Reviewcited by 67
  4. 2017Adaptive Quantization for Deep Neural Networkcited by 67
  5. 2019Long and Diverse Text Generation with Planning-based Hierarchical Variational Modelcited by 62
  6. 2018DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Textcited by 40
  7. 2017Maximum-Likelihood Augmented Discrete Generative Adversarial Networkscited by 39
  8. 2019Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Datacited by 31
  9. 2017Practical Locally Private Heavy Hitterscited by 29
  10. 2020LinkedIn's Audience Engagements API: A Privacy Preserving Data Analytics System at Scalecited by 26
  11. 2018Differential Privacy Techniques for Cyber Physical Systems: A Surveycited by 21
  12. 2020Heterogeneous Federated Learningcited by 19
  13. 2019Local Differential Privacy: a tutorialcited by 13
  14. 2021Privacy and Trust Redefined in Federated Machine Learningcited by 13
  15. 2020BlockFLow: An Accountable and Privacy-Preserving Solution for Federated Learningcited by 12
  16. 2019ARAML: A Stable Adversarial Training Framework for Text Generationcited by 9
  17. 2018Shrinkwrap: Differentially-Private Query Processing in Private Data Federationscited by 5
  18. 2021Secure Random Sampling in Differential Privacycited by 5
  19. 2016Optimal Differentially Private Mechanisms for Randomised Responsecited by 3
  20. 2021AMI-FML: A Privacy-Preserving Federated Machine Learning Framework for AMIcited by 2
  21. 2021Towards Prior-Free Approximately Truthful One-Shot Auction Learning via Differential Privacycited by 1
  22. 2021Federated Two-stage Learning with Sign-based Votingcited by 1

Built on by

Not cited yet.