mlsanityData to 7 Oct 2026

A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning

arXiv 2206.04621 ↗First posted 9 Jun 2022cs.CR cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

We review the use of differential privacy (DP) for privacy protection in machine learning (ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP-based ML implementations are so loose that they do not offer the ex ante privacy guarantees of DP. Instead, what they deliver is basically noise addition similar to the traditional (and often criticized) statistical disclosure control approach. Due to the lack of formal privacy guarantees, the actual level of privacy offered must be experimentally assessed ex post, which is done very seldom. In this respect, we present empirical results showing that standard anti-overfitting techniques in ML can achieve a better utility/privacy/efficiency trade-off than DP.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 24 of its 56 references that are in the map. First posted on arXiv 9 Jun 2022.

Builds on

24 of 56 references.

References · 24

  1. 2016Deep Learning with Differential Privacycited by 2,682
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2017Renyi Differential Privacycited by 643
  4. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  5. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  6. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  7. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  8. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  9. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  10. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
  11. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  12. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
12 more
  1. 2017Collecting Telemetry Data Privatelycited by 147
  2. 2018D2: Decentralized Training over Decentralized Datacited by 140
  3. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  4. 2020Tempered Sigmoid Activations for Deep Learning with Differential Privacycited by 121
  5. 2019Federated Learning for Emoji Prediction in a Mobile Keyboardcited by 115
  6. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 72
  7. 2019Federated Learning with Bayesian Differential Privacycited by 60
  8. 2018DP-ADMM: ADMM-based Distributed Learning with Differential Privacycited by 41
  9. 2020Achieving Security and Privacy in Federated Learning Systems: Survey, Research Challenges and Future Directionscited by 25
  10. 2020The Limits of Differential Privacy (and its Misuse in Data Release and Machine Learning)cited by 22
  11. 2020Voting-based Approaches For Differentially Private Federated Learningcited by 14
  12. 2018Differentially-Private "Draw and Discard" Machine Learningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 9; 2024: 4; 2025: 9; 2026: 3.

27 papers.

Sort:

By area:

  1. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 150
  2. 2023Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generationcited by 94
  3. 2023Locally Differentially Private Document Generation Using Zero Shot Promptingcited by 63
  4. 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 18
  5. 2023Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Surveycited by 12
  6. 2023Protect Your Score: Contact Tracing With Differential Privacy Guaranteescited by 5
  7. 2022GRAIMATTER Green Paper: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)cited by 4
  8. 2023Holistic Survey of Privacy and Fairness in Machine Learningcited by 4
  9. 2022Enhanced Security and Privacy via Fragmented Federated Learningcited by 3
  10. 2025A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attackcited by 2
  11. 2025Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Reviewcited by 2
  12. 2025Improving Epidemic Analyses with Privacy-Preserving Integration of Sensitive Datacited by 2
15 more
  1. 2025Privacy Preserving In-Context-Learning Framework for Large Language Modelscited by 2
  2. 2024Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquirycited by 1
  3. 2025Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligencecited by 1
  4. 2025Membership Inference Attacks Beyond Overfittingcited by 1
  5. 2023When Evolutionary Computation Meets Privacycited by 0
  6. 2023An Examination of the Alleged Privacy Threats of Confidence-Ranked Reconstruction of Census Microdatacited by 0
  7. 2024DNA: Differentially private Neural Augmentation for contact tracingcited by 0
  8. 2024Privacy-Preserving and Trustworthy Deep Learning for Medical Imagingcited by 0
  9. 2024Evaluating utility in synthetic banking microdata applicationscited by 0
  10. 2025Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)cited by 0
  11. 2025Enhancing Differentially Private Linear Regression via Public Second-Momentcited by 0
  12. 2025Balancing Utility and Privacy: Dynamically Private SGD with Random Projectioncited by 0
  13. 2026Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utilitycited by 0
  14. 2026RAPID: Risk of Attribute Prediction-Induced Disclosure in Synthetic Microdatacited by 0
  15. 2026A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attackscited by 0