Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanation manipulation.
Jun 14, 2021 · In this paper, we investigate the capability of fairwashing attacks by analyzing their fidelity-unfairness trade-offs.
Nov 9, 2021 · This paper attempts to empirically characterize the risk of "fair washing" attacks, in which an unfair model can be described with high fidelity ...
Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanations' manipulation.
This paper shows that fairwashed explanation models can generalize beyond the suing group (i.e., data points that are being explained), meaning that a ...
Characterizing the risk of fairwashing. Anonymous Author(s). Affiliation. Address email. Abstract. Fairwashing refers to the risk that an unfair black-box model ...
Dec 11, 2021 · Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanation manipulation.
Characterizing the risk of fairwashing. This repository contains the code to reproduce the experiments in our paper Characterizing the risk of fairwashing.
Dec 6, 2021 · Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanations' manipulation.
Nov 3, 2021 · Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanation manipulation.