A Multidimensional Approach to Ethical AI Auditing

The increasing integration of Artificial Intelligence (AI) across various sectors of society raises complex ethical challenges requiring systematic and scalable oversight mechanisms. While tools such as AIF360 and Aequitas address specific dimensions, namely fairness, there remains a lack of comprehensive frameworks capable of auditing multiple ethical principles simultaneously. This paper introduces a multidimensional AI auditing tool designed to evaluate systems across key dimensions: fairness, explainability, robustness, transparency, bias, sustainability, and legal compliance. Unlike existing tools, our framework enables simultaneous assessment of these dimensions, supporting more holistic and accountable AI deployment. We demonstrate the tool’s applicability through use cases and discuss its implications for building trust and aligning AI development with fundamental ethical standards.

Authors

Institutions

Publication Details

Journal
Proceedings of the AAAI/ACM Conference on AI Ethics and Society
Published
2025-10-15
DOI
https://doi.org/10.1609/aies.v8i3.36732
Primary Topic
Ethics and Social Impacts of AI
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A Multidimensional Approach to Ethical AI Auditing

Jack O'Keefe, Dilhan J. Thilakarathne, Monowar Bhuyan, Virginia Dignum et al.
Proceedings of the AAAI/ACM Conference on AI Ethics and Society
Ethics and Social Impacts of AI
article

A Multidimensional Approach to Ethical AI Auditing

Jack O'Keefe, Dilhan J. Thilakarathne, Monowar Bhuyan, Virginia Dignum, Sónia Teixeira, Carmela Comito, Nina Khairova, Àtia Cortés, Tosin Adewumi, Devvjiit Bhuyan, João Gama, Gianmarco Gori, Marco Minici
article en

Abstract

The increasing integration of Artificial Intelligence (AI) across various sectors of society raises complex ethical challenges requiring systematic and scalable oversight mechanisms. While tools such as AIF360 and Aequitas address specific dimensions, namely fairness, there remains a lack of comprehensive frameworks capable of auditing multiple ethical principles simultaneously. This paper introduces a multidimensional AI auditing tool designed to evaluate systems across key dimensions: fairness, explainability, robustness, transparency, bias, sustainability, and legal compliance. Unlike existing tools, our framework enables simultaneous assessment of these dimensions, supporting more holistic and accountable AI deployment. We demonstrate the tool’s applicability through use cases and discuss its implications for building trust and aligning AI development with fundamental ethical standards.

Proceedings of the AAAI/ACM Conference on AI Ethics and SocietyVol. 8(3)
Vrije Universiteit Brussel (BE), Luleå University of Technology (SE), Barcelona Supercomputing Center (ES), INESC TEC (PT), Umeå University (SE), Universitat Politècnica de Catalunya (ES)
European Commission, Fundação para a Ciência e a Tecnologia
Openalex Percentile: Top 71%
Ethics and Social Impacts of AI
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

A Multidimensional Approach to Ethical AI Auditing — Jack O'Keefe, Dilhan J. Thilakarathne, et al. · Proceedings of the AAAI/ACM Conference on AI Ethics and Society (2025) | TGRS Research Map | TGRS