MDFA: Multi-differential fairness auditor for black box classifiers

4Citations
Citations of this article
36Readers
Mendeley users who have this article in their library.

Abstract

Machine learning algorithms are increasingly involved in sensitive decision-making processes with adverse implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the victims of a classifier's discrimination. We measure discrimination as a violation of multi-differential fairness. Multi-differential fairness is a guarantee that a black box classifier's outcomes do not leak information on the sensitive attributes of a small group of individuals. We reduce the problem of identifying worst-case violations to matching distributions and predicting where sensitive attributes and classifier's outcomes coincide. We apply mdfa to a recidivism risk assessment classifier and demonstrate that for individuals with little criminal history, identified African-Americans are three-times more likely to be considered at high risk of violent recidivism than similar non-African-Americans.

Cite

CITATION STYLE

APA

Gitiaux, X., & Rangwala, H. (2019). MDFA: Multi-differential fairness auditor for black box classifiers. In IJCAI International Joint Conference on Artificial Intelligence (Vol. 2019-August, pp. 5871–5879). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2019/814

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free