Home // PESARO 2025, The Fifteenth International Conference on Performance, Safety and Robustness in Complex Systems and Applications // View article

An End-to-end Method for Operationalizing Trustwothiness in AI-based Critical Systems

Authors:
Karla Quintero
Lucas Mattioli
Henri Sohier
Juliette Mattioli

Keywords: Trustworthy AI, safety-critical AI-based systems, end-to-end engineering of AI-based processes, trustworthiness attributes.

Abstract:
This work presents one of the products of the Confiance.ai research program which addresses an end-to-end method for engineering trustworthy ML-based systems. The proposed methodology revisits software and systems engineering as it encompasses all development phases of the system while integrating the specificities related to the development of ML-based components within the system. The method leverages vastly researched and deployed standard procedures from design to validation and maintenance in order to provide rigor, structure and traceability when developing ML-models.

Pages: 14 to 21

Copyright: Copyright (c) IARIA, 2025

Publication date: May 18, 2025

Published in: conference

ISSN: 2308-3700

ISBN: 978-1-68558-280-7

Location: Nice, France

Dates: from May 18, 2025 to May 22, 2025