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

arXiv: https://arxiv.org/abs/2011.02352 · HTML: https://mlsanity.com/paper/2011.02352/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2020.

## Built on by (most cited first, 22 of 22)

- [On the Impossible Safety of Large AI Models](https://mlsanity.com/paper/2209.15259/) (2022)
- [A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning](https://mlsanity.com/paper/2206.04621/) (2022)
- [Fairness, Integrity, and Privacy in a Scalable Blockchain-based Federated Learning System](https://mlsanity.com/paper/2111.06290/) (2021)
- [A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources](https://mlsanity.com/paper/2203.07018/) (2022)
- [k-Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifiers](https://mlsanity.com/paper/2102.04763/) (2021)
- [Conflicting Interactions Among Protection Mechanisms for Machine Learning Models](https://mlsanity.com/paper/2207.01991/) (2022)
- [Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains](https://mlsanity.com/paper/2410.08327/) (2024)
- [Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources](https://mlsanity.com/paper/2305.06217/) (2023)
- [Generative Data Refinement: Just Ask for Better Data](https://mlsanity.com/paper/2509.08653/) (2025)
- [Enhanced Security and Privacy via Fragmented Federated Learning](https://mlsanity.com/paper/2207.05978/) (2022)
- [GRAIMATTER Green Paper: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)](https://mlsanity.com/paper/2211.01656/) (2022)
- [Blockchain-Empowered Trustworthy Data Sharing: Fundamentals, Applications, and Challenges](https://mlsanity.com/paper/2303.06546/) (2023)
- [Sharper Bounds for Chebyshev Moment Matching, with Applications](https://mlsanity.com/paper/2408.12385/) (2024)
- [Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancements](https://mlsanity.com/paper/2306.10043/) (2023)
- [Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning](https://mlsanity.com/paper/2506.14515/) (2025)
- [A Roadmap for Greater Public Use of Privacy-Sensitive Government Data: Workshop Report](https://mlsanity.com/paper/2208.01636/) (2022)
- [When Evolutionary Computation Meets Privacy](https://mlsanity.com/paper/2304.01205/) (2023)
- [Statistical properties and privacy guarantees of an original distance-based fully synthetic data generation method](https://mlsanity.com/paper/2310.06571/) (2023)
- [An Examination of the Alleged Privacy Threats of Confidence-Ranked Reconstruction of Census Microdata](https://mlsanity.com/paper/2311.03171/) (2023)
- [Evaluating utility in synthetic banking microdata applications](https://mlsanity.com/paper/2410.22519/) (2024)
- [RAPID: Risk of Attribute Prediction-Induced Disclosure in Synthetic Microdata](https://mlsanity.com/paper/2602.09235/) (2026)
- [Shapley-Value-Based Feature Attribution for Data Masking](https://mlsanity.com/paper/2607.28946/) (2026)

## 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.