DeepAI AI Chat
Log In Sign Up

Blind Justice: Fairness with Encrypted Sensitive Attributes

by   Niki Kilbertus, et al.

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.


Learning Fair Models without Sensitive Attributes: A Generative Approach

Most existing fair classifiers rely on sensitive attributes to achieve f...

Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access

Fair machine learning methods seek to train models that balance model pe...

Causal Multi-Level Fairness

Algorithmic systems are known to impact marginalized groups severely, an...

Human-Guided Fair Classification for Natural Language Processing

Text classifiers have promising applications in high-stake tasks such as...

Fair Learning with Private Demographic Data

Sensitive attributes such as race are rarely available to learners in re...

Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Features

Machine learning models often learn to make predictions that rely on sen...

pyCANON: A Python library to check the level of anonymity of a dataset

Openly sharing data with sensitive attributes and privacy restrictions i...