Skip to Main content Skip to Navigation
New interface
Conference papers

Engineering Dependable AI Systems

Abstract : If AI algorithms are now pervasive in our daily life, they essentially deliver non-critical services, i.e., services which failures remain socially and economically acceptable. In order to introduce those algorithms in critical systems, new engineering practices must be defined to give a justified trust in the capability of the system to deliver the intended services. In this paper, we give an overview of the approach that we have put in place to reach this goal in the framework of the French Confiance.ai program. Based on the needs of the industrial partners of the program, we propose a model-based analysis framework capturing the two dimensions of the problem: the one related to the development and operation of the system and the one related to the trust in the system.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03700300
Contributor : Fabien Tschirhart Connect in order to contact the contributor
Submitted on : Wednesday, June 22, 2022 - 9:17:55 AM
Last modification on : Tuesday, October 18, 2022 - 8:34:05 AM
Long-term archiving on: : Friday, September 23, 2022 - 6:05:44 PM

File

SoSE_2022_EC1_EC2_EC6.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03700300, version 1

Citation

Morayo Adedjouma, Christophe Alix, Loic Cantat, Eric Jenn, Juliette Mattioli, et al.. Engineering Dependable AI Systems. 17th Annual System of Systems Engineering Conference (SOSE), IEEE, Jun 2022, Rochester, United States. ⟨hal-03700300⟩

Share

Metrics

Record views

131

Files downloads

30