CryptoCredit: Securely Training Fair Models

10/09/2020
by   Leo de Castro, et al.
0

When developing models for regulated decision making, sensitive features like age, race and gender cannot be used and must be obscured from model developers to prevent bias. However, the remaining features still need to be tested for correlation with sensitive features, which can only be done with the knowledge of those features. We resolve this dilemma using a fully homomorphic encryption scheme, allowing model developers to train linear regression and logistic regression models and test them for possible bias without ever revealing the sensitive features in the clear. We demonstrate how it can be applied to leave-one-out regression testing, and show using the adult income data set that our method is practical to run.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

12/28/2018

A Descriptive Study of Variable Discretization and Cost-Sensitive Logistic Regression on Imbalanced Credit Data

Training classification models on imbalanced data sets tends to result i...
02/17/2022

Conjugate priors and bias reduction for logistic regression models

Logistic regression models for binomial responses are routinely used in ...
09/28/2021

VoxCeleb Enrichment for Age and Gender Recognition

VoxCeleb datasets are widely used in speaker recognition studies. Our wo...
06/08/2018

Blind Justice: Fairness with Encrypted Sensitive Attributes

Recent work has explored how to train machine learning models which do n...
10/30/2021

Identifying and mitigating bias in algorithms used to manage patients in a pandemic

Numerous COVID-19 clinical decision support systems have been developed....
03/22/2021

Detecting Racial Bias in Jury Selection

To support the 2019 U.S. Supreme Court case "Flowers v. Mississippi", AP...
12/02/2020

IBM Employee Attrition Analysis

In this paper, we analyzed the dataset IBM Employee Attrition to find th...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.