Skip to Content
CryptographyCryptography
  • Article
  • Open Access

28 October 2022

16 Pages

Privacy-Preserving Contrastive Explanations with Local Foil Trees

,
and
1
Unit ICT, TNO, 2595 DA The Hague, The Netherlands
2
Services and Cybersecurity Group, University of Twente, 7522 NH Enschede, The Netherlands
*
Author to whom correspondence should be addressed.

Abstract

We present the first algorithm that combines privacy-preserving technologies and state-of-the-art explainable AI to enable privacy-friendly explanations of black-box AI models. We provide a secure algorithm for contrastive explanations of black-box machine learning models that securely trains and uses local foil trees. Our work shows that the quality of these explanations can be upheld whilst ensuring the privacy of both the training data and the model itself.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.