mlsanityData to 7 Oct 2026

Three Tools for Practical Differential Privacy

arXiv 1812.02890 ↗First posted 7 Dec 2018stat.ML cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy attacks are often required to test model privacy. We introduce three tools to make differentially private machine learning more practical: (1) simple sanity checks which can be carried out in a centralized manner before training, (2) an adaptive clipping bound to reduce the effective number of tuneable privacy parameters, and (3) we show that large-batch training improves model performance.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 6; 2023: 5; 2024: 3; 2025: 2.

20 papers.

Sort:

By area:

  1. 2022Mixed Differential Privacy in Computer Visioncited by 53
  2. 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
  3. 2022Differentially Private Learning with Per-Sample Adaptive Clippingcited by 21
  4. 2023Practical Differentially Private Hyperparameter Tuning with Subsamplingcited by 19
  5. 2021Gradient Leakage Attack Resilient Deep Learningcited by 17
  6. 2022Adap DP-FL: Differentially Private Federated Learning with Adaptive Noisecited by 12
  7. 2023DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Releasecited by 9
  8. 2021Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Designcited by 6
  9. 2021Efficient Hyperparameter Optimization for Differentially Private Deep Learningcited by 5
  10. 2024Can LLMs be Fooled? Investigating Vulnerabilities in LLMscited by 5
  11. 2022On the Importance of Architecture and Feature Selection in Differentially Private Machine Learningcited by 3
  12. 2023Batch Clipping and Adaptive Layerwise Clipping for Differential Private Stochastic Gradient Descentcited by 3
8 more
  1. 2023Coupling public and private gradient provably helps optimizationcited by 3
  2. 2025Empirical Privacy Variancecited by 3
  3. 2022How Much User Context Do We Need? Privacy by Design in Mental Health NLP Applicationcited by 2
  4. 2024R+R:Understanding Hyperparameter Effects in DP-SGDcited by 1
  5. 2024Enhancing DP-SGD through Non-monotonous Adaptive Scaling Gradient Weightcited by 1
  6. 2021NanoBatch Privacy: Enabling fast Differentially Private learning on the IPUcited by 0
  7. 2023Exploring Machine Learning Privacy/Utility trade-off from a hyperparameters Lenscited by 0
  8. 2025Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)cited by 0