CUED Publications database

Blind Justice: Fairness with Encrypted Sensitive Attributes

Kilbertus, N and Gascón, A and Kusner, MJ and Veale, M and Gummadi, KP and Weller, A Blind Justice: Fairness with Encrypted Sensitive Attributes. In: 35th International Conference on Machine Learning, 2018-7-10 to 2018-7-15, Stockholmsmässan, Stockholm Sweden pp. 2630-2639.. (Unpublished)

Full text not available from this repository.


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.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: Cryptography and Security Computers and Society Machine Learning
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 13 Jun 2018 20:07
Last Modified: 30 Mar 2021 07:26