mlsanityData to 14 Oct 2026

Differential Privacy in Machine Learning: A Survey from Symbolic AI to LLMs

arXiv 2506.11687 ↗First posted 13 Jun 2025cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data point does not significantly alter the output of an algorithm, thus limiting the exposure of private information. This survey reviews the foundational definitions of differential privacy and traces their evolution through key theoretical and applied contributions. It then provides an in-depth examination of how DP has been integrated into machine learning models, analyzing existing proposals and methods to preserve privacy when training ML models. Finally, it describes how DP-based ML techniques can be evaluated in practice. By offering a comprehensive overview of differential privacy in machine learning, this work aims to contribute to the ongoing development of secure and responsible AI systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 58 references that are in the map. First posted on arXiv 13 Jun 2025.

Builds on

16 of 58 references.

References · 16

  1. 2019Deep Double Descent: Where Bigger Models and More Data Hurtcited by 672
  2. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  3. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 153
  4. 2016Minimax Optimal Procedures for Locally Private Estimationcited by 107
  5. 2021Winning the NIST Contest: A scalable and general approach to differentially private synthetic datacited by 102
  6. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 77
  7. 2021Selective Differential Privacy for Language Modelingcited by 62
  8. 2021ADePT: Auto-encoder based Differentially Private Text Transformationcited by 31
  9. 2017Towards Practical Differential Privacy for SQL Queriescited by 19
  10. 2016Differentially Private Random Decision Forests using Smooth Sensitivitycited by 16
  11. 2019Automatic Discovery of Privacy-Utility Pareto Frontscited by 16
  12. 2022OpBoost: A Vertical Federated Tree Boosting Framework Based on Order-Preserving Desensitizationcited by 12
4 more
  1. 2023Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Surveycited by 12
  2. 2022Post-processing of Differentially Private Data: A Fairness Perspectivecited by 9
  3. 2021DPSyn: Experiences in the NIST Differential Privacy Data Synthesis Challengescited by 7
  4. 2020Deconvoluting Kernel Density Estimation and Regression for Locally Differentially Private Datacited by 4

Built on by

Not cited yet.