mlsanityData to 7 Oct 2026

The Limits of Differential Privacy (and its Misuse in Data Release and Machine Learning)

arXiv 2011.02352 ↗First posted 4 Nov 2020cs.CRcited by 22

Not on the map. Why?

Abstract (arXiv)

Differential privacy (DP) is a neat privacy definition that can co-exist with certain well-defined data uses in the context of interactive queries. However, DP is neither a silver bullet for all privacy problems nor a replacement for all previous privacy models. In fact, extreme care should be exercised when trying to extend its use beyond the setting it was designed for. This paper reviews the limitations of DP and its misuse for individual data collection, individual data release, and machine learning.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 7; 2023: 6; 2024: 3; 2025: 2; 2026: 2.

22 papers.

Sort:

By area:

  1. 2022A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learningcited by 27
  2. 2022On the Impossible Safety of Large AI Modelscited by 27
  3. 2021Fairness, Integrity, and Privacy in a Scalable Blockchain-based Federated Learning Systemcited by 16
  4. 2022A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sourcescited by 13
  5. 2021k-Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifierscited by 12
  6. 2022Conflicting Interactions Among Protection Mechanisms for Machine Learning Modelscited by 12
  7. 2024Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domainscited by 12
  8. 2023Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sourcescited by 10
  9. 2025Generative Data Refinement: Just Ask for Better Datacited by 6
  10. 2022GRAIMATTER Green Paper: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)cited by 4
  11. 2022Enhanced Security and Privacy via Fragmented Federated Learningcited by 3
  12. 2023Blockchain-Empowered Trustworthy Data Sharing: Fundamentals, Applications, and Challengescited by 3
10 more
  1. 2024Sharper Bounds for Chebyshev Moment Matching, with Applicationscited by 3
  2. 2023Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancementscited by 2
  3. 2025Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearningcited by 2
  4. 2022A Roadmap for Greater Public Use of Privacy-Sensitive Government Data: Workshop Reportcited by 1
  5. 2023When Evolutionary Computation Meets Privacycited by 0
  6. 2023Statistical properties and privacy guarantees of an original distance-based fully synthetic data generation methodcited by 0
  7. 2023An Examination of the Alleged Privacy Threats of Confidence-Ranked Reconstruction of Census Microdatacited by 0
  8. 2024Evaluating utility in synthetic banking microdata applicationscited by 0
  9. 2026RAPID: Risk of Attribute Prediction-Induced Disclosure in Synthetic Microdatacited by 0
  10. 2026Shapley-Value-Based Feature Attribution for Data Maskingcited by 0