Ensuring Fairness with Transparent Auditing of Quantitative Bias in AI Systems
This addresses fairness issues in AI decision-making for stakeholders like auditors and developers, but it is incremental as it builds on existing fairness measures with a new tool.
The paper tackles the problem of AI systems exhibiting biases, such as the COMPAS system favoring racial majority groups, by presenting a framework and open-source tool for transparent auditing of fairness, enabling third-party auditors, developers, and the public to systematically examine AI systems.
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.