Establishing and Evaluating Trustworthy AI: Overview and Research Challenges
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910699478843392 |
|---|---|
| author | Kowald, Dominik Scher, Sebastian Pammer-Schindler, Viktoria Müllner, Peter Waxnegger, Kerstin Demelius, Lea Fessl, Angela Toller, Maximilian Estrada, Inti Gabriel Mendoza Simic, Ilija Sabol, Vedran Truegler, Andreas Veas, Eduardo Kern, Roman Nad, Tomislav Kopeinik, Simone |
| author_facet | Kowald, Dominik Scher, Sebastian Pammer-Schindler, Viktoria Müllner, Peter Waxnegger, Kerstin Demelius, Lea Fessl, Angela Toller, Maximilian Estrada, Inti Gabriel Mendoza Simic, Ilija Sabol, Vedran Truegler, Andreas Veas, Eduardo Kern, Roman Nad, Tomislav Kopeinik, Simone |
| contents | Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a result, there has been a surge in public and academic discussions about aspects that AI systems must fulfill to be considered trustworthy. In this paper, we synthesize existing conceptualizations of trustworthy AI along six requirements: 1) human agency and oversight, 2) fairness and non-discrimination, 3) transparency and explainability, 4) robustness and accuracy, 5) privacy and security, and 6) accountability. For each one, we provide a definition, describe how it can be established and evaluated, and discuss requirement-specific research challenges. Finally, we conclude this analysis by identifying overarching research challenges across the requirements with respect to 1) interdisciplinary research, 2) conceptual clarity, 3) context-dependency, 4) dynamics in evolving systems, and 5) investigations in real-world contexts. Thus, this paper synthesizes and consolidates a wide-ranging and active discussion currently taking place in various academic sub-communities and public forums. It aims to serve as a reference for a broad audience and as a basis for future research directions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_09973 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Establishing and Evaluating Trustworthy AI: Overview and Research Challenges Kowald, Dominik Scher, Sebastian Pammer-Schindler, Viktoria Müllner, Peter Waxnegger, Kerstin Demelius, Lea Fessl, Angela Toller, Maximilian Estrada, Inti Gabriel Mendoza Simic, Ilija Sabol, Vedran Truegler, Andreas Veas, Eduardo Kern, Roman Nad, Tomislav Kopeinik, Simone Machine Learning Information Retrieval Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a result, there has been a surge in public and academic discussions about aspects that AI systems must fulfill to be considered trustworthy. In this paper, we synthesize existing conceptualizations of trustworthy AI along six requirements: 1) human agency and oversight, 2) fairness and non-discrimination, 3) transparency and explainability, 4) robustness and accuracy, 5) privacy and security, and 6) accountability. For each one, we provide a definition, describe how it can be established and evaluated, and discuss requirement-specific research challenges. Finally, we conclude this analysis by identifying overarching research challenges across the requirements with respect to 1) interdisciplinary research, 2) conceptual clarity, 3) context-dependency, 4) dynamics in evolving systems, and 5) investigations in real-world contexts. Thus, this paper synthesizes and consolidates a wide-ranging and active discussion currently taking place in various academic sub-communities and public forums. It aims to serve as a reference for a broad audience and as a basis for future research directions. |
| title | Establishing and Evaluating Trustworthy AI: Overview and Research Challenges |
| topic | Machine Learning Information Retrieval |
| url | https://arxiv.org/abs/2411.09973 |