Accuracy, Interpretability, and Differential Privacy via Explainable Boosting

06/17/2021
by   Harsha Nori, et al.
0

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.

READ FULL TEXT

page 2

page 9

research
07/22/2020

Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising

Deep learning models leak significant amounts of information about their...
research
05/28/2019

Differential Privacy Has Disparate Impact on Model Accuracy

Differential privacy (DP) is a popular mechanism for training machine le...
research
02/22/2022

Differentially Private Estimation of Heterogeneous Causal Effects

Estimating heterogeneous treatment effects in domains such as healthcare...
research
03/22/2023

Exploring the Benefits of Visual Prompting in Differential Privacy

Visual Prompting (VP) is an emerging and powerful technique that allows ...
research
02/15/2023

DP-BART for Privatized Text Rewriting under Local Differential Privacy

Privatized text rewriting with local differential privacy (LDP) is a rec...
research
06/24/2021

DPSyn: Experiences in the NIST Differential Privacy Data Synthesis Challenges

We summarize the experience of participating in two differential privacy...
research
01/21/2019

Differential Privacy for Power Grid Obfuscation

The availability of high-fidelity energy networks brings significant val...

Please sign up or login with your details

Forgot password? Click here to reset