Leveraging Tropical Algebra to Assess Trustworthy AI
DOI:
https://doi.org/10.1609/aaaiss.v4i1.31775Abstract
Given the complexity of the application domain, the qualitative and quantifiable nature of the concepts involved, the wide heterogeneity and granularity of trustworthy attributes, and in some cases the non-comparability of the latter, assessing the trustworthiness of AI-based systems is a challenging process. In order to overcome these challenges, the Confiance.ai program proposes an innovative solution based on a Multi-Criteria Decision Aiding (MCDA) methodology. This approach involves several stages: framing trustworthiness as a set of well-defined attributes, exploring attributes to determine related Key Performance Indicators (KPI) or metrics, selecting evaluation protocols, and defining a method to aggregate multiple criteria to estimate an overall assessment of trust. This approach is illustrated by applying the RUM methodology (Robustness, Uncertainty, Monitoring) to ML context, while the focus on aggregation methods are based on Tropical Algebra.Downloads
Published
2024-11-08
How to Cite
Mattioli, J., Gonzalez, M., Mattioli, L., Quintero, K., & Sohier, H. (2024). Leveraging Tropical Algebra to Assess Trustworthy AI. Proceedings of the AAAI Symposium Series, 4(1), 81-88. https://doi.org/10.1609/aaaiss.v4i1.31775
Issue
Section
AI Trustworthiness and Risk Assessment for Challenging Contexts (ATRACC)