mlsanityData to 14 Oct 2026

Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey

arXiv 2309.16398 ↗First posted 28 Sep 2023cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Differential Privacy has become a widely popular method for data protection in machine learning, especially since it allows formulating strict mathematical privacy guarantees. This survey provides an overview of the state-of-the-art of differentially private centralized deep learning, thorough analyses of recent advances and open problems, as well as a discussion of potential future developments in the field. Based on a systematic literature review, the following topics are addressed: auditing and evaluation methods for private models, improvements of privacy-utility trade-offs, protection against a broad range of threats and attacks, differentially private generative models, and emerging application domains.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 70 of its 153 references that are in the map. First posted on arXiv 28 Sep 2023.

Builds on

70 of 153 references.

References · 70

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2016Deep Learning with Differential Privacycited by 2,728
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  6. 2017Improved Training of Wasserstein GANscited by 2,235
  7. 2020Extracting Training Data from Large Language Modelscited by 2,189
  8. 2019Machine Unlearningcited by 1,061
  9. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  10. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  11. 2017Renyi Differential Privacycited by 650
  12. 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 637
38 more
  1. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  2. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 412
  3. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 348
  4. 2019Why gradient clipping accelerates training: A theoretical justification for adaptivitycited by 341
  5. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  6. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 246
  7. 2018Differentially Private Generative Adversarial Networkcited by 235
  8. 2020Differentially Private Learning Needs Better Features (or Much More Data)cited by 235
  9. 2020Auditing Differentially Private Machine Learning: How Private is Private SGD?cited by 218
  10. 2018Adversarial Robustness Toolbox v1.0.0cited by 215
  11. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 199
  12. 2020When Machine Unlearning Jeopardizes Privacycited by 198
  13. 2022What Does it Mean for a Language Model to Preserve Privacy?cited by 195
  14. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 175
  15. 2022Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attackscited by 175
  16. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  17. 2016Concentrated Differential Privacycited by 144
  18. 2020Understanding Gradient Clipping in Private SGD: A Geometric Perspectivecited by 142
  19. 2020Tempered Sigmoid Activations for Deep Learning with Differential Privacycited by 122
  20. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  21. 2020Synthetic Data -- Anonymisation Groundhog Daycited by 108
  22. 2022Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipecited by 108
  23. 2019Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacycited by 95
  24. 2022Position: Considerations for Differentially Private Learning with Large-Scale Public Pretrainingcited by 88
  25. 2020Causal Interpretability for Machine Learning -- Problems, Methods and Evaluationcited by 82
  26. 2018Private Selection from Private Candidatescited by 75
  27. 2019Differentially Private Model Publishing for Deep Learningcited by 71
  28. 2020Privacy in Deep Learning: A Surveycited by 71
  29. 2020When Machine Learning Meets Privacy: A Survey and Outlookcited by 68
  30. 2020Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacycited by 61
  31. 2020Survey on Causal-based Machine Learning Fairness Notionscited by 54
  32. 2018Generalised Differential Privacy for Text Document Processingcited by 52
  33. 2020Differentially Private Synthetic Medical Data Generation using Convolutional GANscited by 52
  34. 2019Leveraging Hierarchical Representations for Preserving Privacy and Utility in Textcited by 50
  35. 2021Graph Embedding for Recommendation against Attribute Inference Attackscited by 40
  36. 2022Debugging Differential Privacy: A Case Study for Privacy Auditingcited by 40
  37. 2017Differentially Private Mixture of Generative Neural Networkscited by 39
  38. 2018Private Model Compression via Knowledge Distillationcited by 37

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 7; 2026: 4.

12 papers.

  1. 2025Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Surveycited by 14
  2. 2025Differential privacy for medical deep learning: methods, tradeoffs, and deployment implicationscited by 7
  3. 2024DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixingcited by 1
  4. 2025Empirical Calibration and Metric Differential Privacy in Language Modelscited by 1
  5. 2026Private Prediction via PAC Privacycited by 1
  6. 2025Differential Privacy in Machine Learning: A Survey from Symbolic AI to LLMscited by 0
  7. 2025PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstructioncited by 0
  8. 2025Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)cited by 0
  9. 2025PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attackscited by 0
  10. 2026Res-MIA: A Training-Free Resolution-Based Membership Inference Attack on Federated Learning Modelscited by 0
  11. 2026Adaptive Sampling and Clipping for Private Worst-Case Group Optimizationcited by 0
  12. 2026Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmapcited by 0