New Paper Accepted: Towards the Assessment of Trustworthy AI: A Catalog-Based Approach
Our paper entitled Towards the Assessment of Trustworthy AI: A Catalog-Based Approach has been accepted and published at the workshop TRUST-AI 2025.
In this paper, we provide an initial version of a certification scheme natively designed for AI-based systems. The scheme is based on a catalog that precisely defines the set of controls to be executed given a target property, as well as the specific phase of the AI life cycle the control insists on.
This work is the first published paper of the PhD student I’m co-supervising, Aneela Nasim. The authors of the paper are Marco Anisetti, Claudio A. Ardagna, Nicola Bena (me), and Aneela Nasim.
Below is the full abstract.
Artificial Intelligence (AI)-based systems are experiencing widespread adoption across a broad range of applications, including critical domains such as law and healthcare. This paradigm shift prompted a push towards the development of trustworthy AI systems, which are increasingly mandated by law and regulations. However, assessment techniques that concretely verify the trustworthiness of AI-based systems are still lacking. Current techniques in fact focus on traditional quality properties, providing either high-level guidelines or low-level techniques that cannot be generalized, and are therefore not applicable to AI-based systems. In this paper, we propose an assessment scheme that builds on a structured catalog of non-functional properties. The support for specific non-functional properties is verified along the entire system life cycle, from data collection to evaluation, by a set of assessment controls.