mlsanityData to 7 Oct 2026

Interpretable and Differentially Private Predictions

arXiv 1906.02004 ↗First posted 5 Jun 2019cs.LG stat.MLcited by 28

Not on the map. Why?

Abstract (arXiv)

Interpretable predictions, where it is clear why a machine learning model has made a particular decision, can compromise privacy by revealing the characteristics of individual data points. This raises the central question addressed in this paper: Can models be interpretable without compromising privacy? For complex big data fit by correspondingly rich models, balancing privacy and explainability is particularly challenging, such that this question has remained largely unexplored. In this paper, we propose a family of simple models in the aim of approximating complex models using several locally linear maps per class to provide high classification accuracy, as well as differentially private explanations on the classification. We illustrate the usefulness of our approach on several image benchmark datasets as well as a medical dataset.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 8; 2023: 7; 2024: 5; 2025: 5; 2026: 1.

28 papers.

Sort:

  1. 2021Towards Personalized Federated Learningcited by 462
  2. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  3. 2024Perturbation-Restrained Sequential Model Editingcited by 27
  4. 2022Inferring Sensitive Attributes from Model Explanationscited by 15
  5. 2023Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Surveycited by 12
  6. 2023A Survey on Explainable Artificial Intelligence for Cybersecuritycited by 9
  7. 2021Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learningcited by 7
  8. 2022SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usabilitycited by 7
  9. 2023Balancing Privacy Protection and Interpretability in Federated Learningcited by 6
  10. 2023SoK: Unintended Interactions among Machine Learning Defenses and Riskscited by 6
  11. 2024A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasurescited by 6
  12. 2023Privacy-Preserving Algorithmic Recoursecited by 5
16 more
  1. 2025Mathematical Foundation of Interpretable Equivariant Surrogate Modelscited by 5
  2. 2022A Differentially Private Framework for Deep Learning with Convexified Loss Functionscited by 4
  3. 2023SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learningcited by 4
  4. 2022The Need for Interpretable Features: Motivation and Taxonomycited by 3
  5. 2022Private Boosted Decision Trees via Smooth Re-Weightingcited by 2
  6. 2022Spending Privacy Budget Fairly and Wiselycited by 2
  7. 2023MLHOps: Machine Learning for Healthcare Operationscited by 2
  8. 2024Differential Privacy for Anomaly Detection: Analyzing the Trade-off Between Privacy and Explainabilitycited by 2
  9. 2024GLEAMS: Bridging the Gap Between Local and Global Explanationscited by 2
  10. 2025Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Reviewcited by 2
  11. 2024Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquirycited by 1
  12. 2025Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligencecited by 1
  13. 2025Towards the Formalization of a Trustworthy AI for Mining Interpretable Models explOiting Sophisticated Algorithmscited by 1
  14. 2025Privacy-Preserving Explainable AIoT Application via SHAP Entropy Regularizationcited by 1
  15. 2022Tensions Between the Proxies of Human Values in AIcited by 0
  16. 2026Where Privacy Belongs: Placement Diagnosis and Certified Selection for Private Counterfactual Explanations on Graphscited by 0