Ensuring Fairness with Transparent Auditing of Quantitative Bias in AI Systems

TL;DR

This paper introduces a transparent, open-source auditing framework and tool for assessing AI fairness, emphasizing third-party evaluation and statistical analysis to identify biases like those seen in the COMPAS recidivism system.

Contribution

It proposes a novel transparent auditing framework with an open-source tool for systematic fairness assessment by third parties, AI developers, and the public.

Findings

Developed an open-source fairness auditing tool

Demonstrated the framework's application on real AI systems

Advocated for transparency and third-party involvement in AI fairness

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.