AutoFairML: An Automated Middleware for Fairness Auditing in Real-world AI Pipelines

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00389740" target="_blank" >RIV/68407700:21230/25:00389740 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICDCSW63273.2025.00050" target="_blank" >https://doi.org/10.1109/ICDCSW63273.2025.00050</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICDCSW63273.2025.00050" target="_blank" >10.1109/ICDCSW63273.2025.00050</a>

Jazyk výsledku

angličtina

Název v původním jazyce

AutoFairML: An Automated Middleware for Fairness Auditing in Real-world AI Pipelines

Popis výsledku v původním jazyce

The great proliferation of Artificial Intelligence in a wide variety of application domains has produced an imminent need to interpret the output of such models, especially for evaluating their fairness. Such domains may include human resources management for evaluating individual and group fairness, advertising and financial technologies, where fairness can have significant impact. However, existing tools like AIF360 and AIX360, although important for helping practitioners in industrial AI pipelines, have significant shortcomings. Such tools suffer from poor scalability and developers cannot directly benefit from, since there is no middleware available to support and take advantage of modern AI infrastructures. In this work, we present AutoFairML, an automated middleware able to leverage existing tools to detect bias in AI/ML models, examine trade-offs between different measures of fairness, certify their fairness a priori and provide explanations for the models. This represents a significant improvement in the usability and the real-world applicability of specialized fairness and explainability toolkits such as AIF360 and AIX360. Our experimental evaluation using real-world pipelines and data highlights its merits in terms of practicality and efficiency.

Název v anglickém jazyce

AutoFairML: An Automated Middleware for Fairness Auditing in Real-world AI Pipelines

Popis výsledku anglicky

The great proliferation of Artificial Intelligence in a wide variety of application domains has produced an imminent need to interpret the output of such models, especially for evaluating their fairness. Such domains may include human resources management for evaluating individual and group fairness, advertising and financial technologies, where fairness can have significant impact. However, existing tools like AIF360 and AIX360, although important for helping practitioners in industrial AI pipelines, have significant shortcomings. Such tools suffer from poor scalability and developers cannot directly benefit from, since there is no middleware available to support and take advantage of modern AI infrastructures. In this work, we present AutoFairML, an automated middleware able to leverage existing tools to detect bias in AI/ML models, examine trade-offs between different measures of fairness, certify their fairness a priori and provide explanations for the models. This represents a significant improvement in the usability and the real-world applicability of specialized fairness and explainability toolkits such as AIF360 and AIX360. Our experimental evaluation using real-world pipelines and data highlights its merits in terms of practicality and efficiency.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings - 2025 IEEE 45th International Conference on Distributed Computing Systems Workshops

ISBN

979-8-3315-1726-7

ISSN

1545-0678

e-ISSN

—

Počet stran výsledku

6

Strana od-do

261-266

Název nakladatele

IEEE Industrial Electronic Society

Místo vydání

Vienna

Místo konání akce

Glasgov

Datum konání akce

20. 7. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001669747800044