LUCID: Exposing Algorithmic Bias through Inverse Design

Carmen Mazijn, Andres Algaba, Jan Danckaert, Vincent Ginis, Carina Prunkl

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

AI systems can createjavascript:void(0);, propagate, support, and automate bias in decision-making processes. To mitigate biased decisions, we both need to understand the origin of the bias and define what it means for an algorithm to make fair decisions. Most group fairness notions assess a model's equality of outcome by computing statistical metrics on the outputs. We argue that these output metrics encounter intrinsic obstacles and present a complementary approach that aligns with the increasing focus on equality of treatment. By Locating Unfairness through Canonical Inverse Design (LUCID), we generate a canonical set that shows the desired inputs for a model given a preferred output. The canonical set reveals the model's internal logic and exposes potential unethical biases by repeatedly interrogating the decision-making process. We evaluate LUCID on the UCI Adult and COMPAS data sets and find that some biases detected by a canonical set differ from those of output metrics. The results show that by shifting the focus towards equality of treatment and looking into the algorithm's internal workings, the canonical sets are a valuable addition to the toolbox of algorithmic fairness evaluation.
Original languageEnglish
JournalProceedings of the AAAI Conference on Artificial Intelligence
DOIs
Publication statusPublished - 26 Jun 2023
Externally publishedYes

Fingerprint

Dive into the research topics of 'LUCID: Exposing Algorithmic Bias through Inverse Design'. Together they form a unique fingerprint.

Cite this