Probabilistic Dataset Reconstruction from Interpretable Models

Understand

Interpretability is often pointed out as a key requirement for trustworthy machine learning.

• However, learning and releasing models that are inherently interpretable leaks information regarding the underlying training data.
• As such disclosure may directly conflict with privacy, a precise quantification of the privacy impact of such breach is a fundamental problem.
• For instance, previous work have shown that the structure of a decision tree can be leveraged to build a probabilistic reconstruction of its training dataset, with the uncertainty of the reconstruction being a relevant metric for the information leak.