# Accuracy, Interpretability, and Differential Privacy via Explainable Boosting

arXiv: https://arxiv.org/abs/2106.09680 · HTML: https://mlsanity.com/paper/2106.09680/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 16 of 16)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [The Composition Theorem for Differential Privacy](https://mlsanity.com/paper/1311.0776/) (2013)
- [InterpretML: A Unified Framework for Machine Learning Interpretability](https://mlsanity.com/paper/1909.09223/) (2019)
- [Deep Learning with Gaussian Differential Privacy](https://mlsanity.com/paper/1911.11607/) (2019)
- [Private Selection from Private Candidates](https://mlsanity.com/paper/1811.07971/) (2018)
- [Diffprivlib: The IBM Differential Privacy Library](https://mlsanity.com/paper/1907.02444/) (2019)
- [How Interpretable and Trustworthy are GAMs?](https://mlsanity.com/paper/2006.06466/) (2020)
- [In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Prediction](https://mlsanity.com/paper/2005.04176/) (2020)
- [Privacy-Preserving Gradient Boosting Decision Trees](https://mlsanity.com/paper/1911.04209/) (2019)
- [Decision Tree Classification with Differential Privacy: A Survey](https://mlsanity.com/paper/1611.01919/) (2016)
- [Differentially Private Bayesian Optimization](https://mlsanity.com/paper/1501.04080/) (2015)
- [Private Approximations of the 2nd-Moment Matrix Using Existing Techniques in Linear Regression](https://mlsanity.com/paper/1507.00056/) (2015)
- [Scalable and Provably Accurate Algorithms for Differentially Private Distributed Decision Tree Learning](https://mlsanity.com/paper/2012.10602/) (2020)

## Built on by (most cited first, 24 of 24)

- [Differentially Private Estimation of Heterogeneous Causal Effects](https://mlsanity.com/paper/2202.11043/) (2022)
- [TimberTrek: Exploring and Curating Sparse Decision Trees with Interactive Visualization](https://mlsanity.com/paper/2209.09227/) (2022)
- [Federated Boosted Decision Trees with Differential Privacy](https://mlsanity.com/paper/2210.02910/) (2022)
- [Quantum Gradient Class Activation Map for Model Interpretability](https://mlsanity.com/paper/2408.05899/) (2024)
- [Differentially Private Optimizers Can Learn Adversarially Robust Models](https://mlsanity.com/paper/2211.08942/) (2022)
- [Improved Differentially Private Regression via Gradient Boosting](https://mlsanity.com/paper/2303.03451/) (2023)
- [Interpretable Survival Analysis for Heart Failure Risk Prediction](https://mlsanity.com/paper/2310.15472/) (2023)
- [SoK: Unintended Interactions among Machine Learning Defenses and Risks](https://mlsanity.com/paper/2312.04542/) (2023)
- [Classification with Partially Private Features](https://mlsanity.com/paper/2312.07583/) (2023)
- [Attention-like feature explanation for tabular data](https://mlsanity.com/paper/2108.04855/) (2021)
- [Additive Models Explained: A Computational Complexity Approach](https://mlsanity.com/paper/2510.21292/) (2025)
- [Spending Privacy Budget Fairly and Wisely](https://mlsanity.com/paper/2204.12903/) (2022)
- [Automation of Quantum Dot Measurement Analysis via Explainable Machine Learning](https://mlsanity.com/paper/2402.13699/) (2024)
- [Differential Privacy for Anomaly Detection: Analyzing the Trade-off Between Privacy and Explainability](https://mlsanity.com/paper/2404.06144/) (2024)
- [Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Review](https://mlsanity.com/paper/2505.02828/) (2025)
- [Model Agnostic Differentially Private Causal Inference](https://mlsanity.com/paper/2505.19589/) (2025)
- [The Computational Complexity of Concise Hypersphere Classification](https://mlsanity.com/paper/2312.07103/) (2023)
- [Towards the Formalization of a Trustworthy AI for Mining Interpretable Models explOiting Sophisticated Algorithms](https://mlsanity.com/paper/2510.20621/) (2025)
- [Explanations Leak: Membership Inference with Differential Privacy and Active Learning Defense](https://mlsanity.com/paper/2602.03611/) (2026)
- [Estimate Deformation Capacity of Non-Ductile RC Shear Walls using Explainable Boosting Machine](https://mlsanity.com/paper/2301.04652/) (2023)
- [Smoothly Giving up: Robustness for Simple Models](https://mlsanity.com/paper/2302.09114/) (2023)
- [An explainable model to support the decision about the therapy protocol for AML](https://mlsanity.com/paper/2307.02631/) (2023)
- [S-BDT: Distributed Differentially Private Boosted Decision Trees](https://mlsanity.com/paper/2309.12041/) (2023)
- [GL-ICNN: An End-To-End Interpretable Convolutional Neural Network for the Diagnosis and Prediction of Alzheimer's Disease](https://mlsanity.com/paper/2501.11715/) (2025)

## Abstract (arXiv)

We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while protecting privacy. Our experiments on multiple classification and regression datasets show that DP-EBM models suffer surprisingly little accuracy loss even with strong differential privacy guarantees. In addition to high accuracy, two other benefits of applying DP to EBMs are: a) trained models provide exact global and local interpretability, which is often important in settings where differential privacy is needed; and b) the models can be edited after training without loss of privacy to correct errors which DP noise may have introduced.