The LCFI website uses cookies only for anonymised website statistics and for ensuring our security, never for tracking or identifying you individually. To find out more, and to find out how we protect your personal information, please read our privacy policy.

Blind Justice: Fairness with Encrypted Sensitive Attributes

Conference Paper by Niki Kilbertus, Adria Gascon, Matt Kusner, Michael Veale, Krishna P. Gummadi, Adrian Weller

Blind Justice: Fairness with Encrypted Sensitive Attributes

35th International Conference on Machine Learning (ICML), Stockholm 2018

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.

Download Conference Paper