Ensuring Fairness with Transparent Auditing of Quantitative Bias in AI Systems

TL;DR

A framework for auditing AI fairness, involving third-party auditors and AI system providers, and a tool to facilitate systematic examination of AI systems are presented, which advocates a transparent white-box and statistics-based approach.

Abstract

With the rapid advancement of AI, there is a growing trend to integrate AI into decision-making processes. However, AI systems may exhibit biases that lead decision-makers to draw unfair conclusions. Notably, the COMPAS system used in the American justice system to evaluate recidivism was found to favor racial majority groups; specifically, it violates a fairness standard called equalized odds. Various measures have been proposed to assess AI fairness. We present a framework for auditing AI fairness, involving third-party auditors and AI system providers, and we have created a tool to facilitate systematic examination of AI systems. The tool is open-sourced and publicly available. Unlike traditional AI systems, we advocate a transparent white-box and statistics-based approach. It can be utilized by third-party auditors, AI developers, or the general public for reference when judging the fairness criterion of AI systems.

Figures (12)

• Figure 1: Unprivileged Group: African-American
• Figure 2: Unprivileged Group: Caucasian
• Figure 3: Unprivileged Group: Asian
• Figure 4: Unprivileged Group: Native American
• Figure 5: Unprivileged Group: Hispanic