AI Systems Trustworthiness Assessment: State of the Art

Afef Awadid, Kahina Amokrane-Ferka, Henri Sohier, Juliette Mattioli, Faouzi Adjed, Martin Gonzalez, Souhaiel Khalfaoui

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collection!!Conference contributionRevue par des pairs

3 Citations (Scopus)

Résumé

Model-based System Engineering (MBSE) has been advocated as a promising approach to reduce the complexity of AI-based systems development. However, given the uncertainties and risks associated with Artificial Intelligence (AI), the successful application of MBSE requires the assessment of AI trustworthiness. To deal with this issue, this paper provides a state of the art review of AI trustworthiness assessment in terms of trustworthiness attributes/ characteristics and their corresponding evaluation metrics. Examples of such attributes include data quality, robustness, and explainability. The proposed review is based on academic and industrial literature conducted within the Confiance.ai research program.

langue originaleAnglais
titreProceedings of the 12th International Conference on Model-Based Software and Systems Engineering
rédacteurs en chefFrancisco José Domínguez Mayo, Luís Ferreira Pires, Edwin Seidewitz
EditeurScience and Technology Publications, Lda
Pages322-333
Nombre de pages12
ISBN (imprimé)9789897586828
Les DOIs
étatPublié - 1 janv. 2024
Modification externeOui
Evénement12th International Conference on Model-Based Software and Systems Engineering, MODELSWARD 2024 - Rome, Italie
Durée: 21 févr. 202423 févr. 2024

Série de publications

NomInternational Conference on Model-Driven Engineering and Software Development
Volume1
ISSN (Electronique)2184-4348

Une conférence

Une conférence12th International Conference on Model-Based Software and Systems Engineering, MODELSWARD 2024
Pays/TerritoireItalie
La villeRome
période21/02/2423/02/24

Contient cette citation