Towards Engineering Processes to Guide the Development of Trustworthy ML Systems - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Towards Engineering Processes to Guide the Development of Trustworthy ML Systems

Afef Awadid
  • Fonction : Auteur
Dominique Tachet
  • Fonction : Auteur
Check Koutame
  • Fonction : Auteur

Résumé

Engineering reliable Machine Learning (ML)-based safety-critical systems, such as autonomous vehicles, requires a comprehensive understanding of the intricate interplay between different disciplines, including among others ML algorithms, systems, and safety engineering. This complexity arises from the dynamic nature of ML models, the uncertainty of real-world data, and the potential for adversarial attacks. To address this challenge, the Confiance.ai research program proposes an end-to-end method to guide the development of trustworthy ML systems. This method includes engineering processes and a set of associated tools, which provide model-based guidelines covering the entire ML systems engineering lifecycle. The proposal is the result of collaboration between multidisciplinary experts focused on the trustworthiness of ML systems. The method is illustrated with an example of an ML model robustness evaluation process.
Fichier non déposé

Dates et versions

hal-04682750 , version 1 (30-08-2024)

Identifiants

  • HAL Id : hal-04682750 , version 1

Citer

Afef Awadid, Boris Robert, Dominique Tachet, Check Koutame, Juliette Mattioli. Towards Engineering Processes to Guide the Development of Trustworthy ML Systems. The IEEE International Symposium on Systems Engineering (ISSE 2024), Oct 2024, Perugia, Italy. ⟨hal-04682750⟩
64 Consultations
0 Téléchargements

Partager

More