Model Reconstruction from Model Explanations

Milli, S; Schmidt, L; Dragan, AD; Hardt, M

Milli, S (reprint author), Univ Calif Berkeley, Berkeley, CA 94720 USA.

FAT*'19: PROCEEDINGS OF THE 2019 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, 2019; (): 1

Abstract

We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension betw......

Full Text Link