Blind Justice: Fairness with Encrypted Sensitive Attributes
Machine Learning
2018-09-06 v1 Cryptography and Security
Computers and Society
Machine Learning
Abstract
Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes should not be considered. On the other hand, in order to avoid disparate impact, sensitive attributes must be examined, e.g., in order to learn a fair model, or to check if a given model is fair. We introduce methods from secure multi-party computation which allow us to avoid both. By encrypting sensitive attributes, we show how an outcome-based fair model may be learned, checked, or have its outputs verified and held to account, without users revealing their sensitive attributes.
Cite
@article{arxiv.1806.03281,
title = {Blind Justice: Fairness with Encrypted Sensitive Attributes},
author = {Niki Kilbertus and Adrià Gascón and Matt J. Kusner and Michael Veale and Krishna P. Gummadi and Adrian Weller},
journal= {arXiv preprint arXiv:1806.03281},
year = {2018}
}
Comments
published at ICML 2018