mlsanityData to 7 Oct 2026

Renyi Differential Privacy

arXiv 1702.07476 ↗First posted 24 Feb 2017cs.CRcited by 643

Not on the map. Why?

Cited by 34 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a natural relaxation of differential privacy based on the Renyi divergence. Closely related notions have appeared in several recent papers that analyzed composition of differentially private mechanisms. We argue that the useful analytical tool can be used as a privacy definition, compactly and accurately representing guarantees on the tails of the privacy loss. We demonstrate that the new definition shares many important properties with the standard definition of differential privacy, while additionally allowing tighter analysis of composite heterogeneous mechanisms.

Key facts. Cited by 643 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 113; 2022: 152; 2023: 133; 2024: 83; 2025: 85; 2026: 77.

643 papers.

Sort:

By area:

  1. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
  2. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 375
  3. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  4. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 193
  5. 2021Numerical Composition of Differential Privacycited by 174
  6. 2021Practical and Private (Deep) Learning without Sampling or Shufflingcited by 169
  7. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 150
  8. 2022Reconstructing Training Data with Informed Adversariescited by 143
  9. 2021On the Importance of Difficulty Calibration in Membership Inference Attackscited by 137
  10. 2021Machine Unlearning via Algorithmic Stabilitycited by 128
  11. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  12. 2023Invisible Image Watermarks Are Provably Removable Using Generative AIcited by 124
38 more
  1. 2022Privacy for Free: How does Dataset Condensation Help Privacy?cited by 119
  2. 2023Privacy Auditing with One (1) Training Runcited by 119
  3. 2022Measuring Forgetting of Memorized Training Examplescited by 118
  4. 2022Differentially Private Diffusion Modelscited by 118
  5. 2024Machine Unlearning of Pre-trained Large Language Modelscited by 118
  6. 2021Large-Scale Differentially Private BERTcited by 117
  7. 2021Hyperparameter Tuning with Renyi Differential Privacycited by 104
  8. 2022Automatic Clipping: Differentially Private Deep Learning Made Easier and Strongercited by 87
  9. 2021Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learningcited by 86
  10. 2022Position: Considerations for Differentially Private Learning with Large-Scale Public Pretrainingcited by 86
  11. 2021Optimal Accounting of Differential Privacy via Characteristic Functioncited by 83
  12. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  13. 2021Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descentcited by 71
  14. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  15. 2022Differentially Private Language Models for Secure Data Sharingcited by 68
  16. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 66
  17. 2022Synthetic Data -- what, why and how?cited by 66
  18. 2022Differentially Private Optimization on Large Model at Small Costcited by 65
  19. 2021Selective Differential Privacy for Language Modelingcited by 61
  20. 2022Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Losscited by 60
  21. 2022Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streamscited by 59
  22. 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
  23. 2022Forget Unlearning: Towards True Data-Deletion in Machine Learningcited by 58
  24. 2021Decentralized Federated Learning through Proxy Model Sharingcited by 56
  25. 2023DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineercited by 56
  26. 2021Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergencecited by 54
  27. 2022Exploring the Limits of Differentially Private Deep Learning with Group-wise Clippingcited by 52
  28. 2021Non-Euclidean Differentially Private Stochastic Convex Optimization: Optimal Rates in Linear Timecited by 51
  29. 2022TAN Without a Burn: Scaling Laws of DP-SGDcited by 51
  30. 2021Membership Inference Attack Susceptibility of Clinical Language Modelscited by 50
  31. 2022Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributionscited by 50
  32. 2023Privacy-Preserving In-Context Learning for Large Language Modelscited by 50
  33. 2024Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearningcited by 48
  34. 2022Private Convex Optimization via Exponential Mechanismcited by 47
  35. 2022GAP: Differentially Private Graph Neural Networks with Aggregation Perturbationcited by 46
  36. 2022Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)cited by 45
  37. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  38. 2023Faster high-accuracy log-concave sampling via algorithmic warm startscited by 44

50 most cited of 643 All 643 (JSON)