Operational Fairness for Facial Authentication Systems

Mélanie Gornet (1, 2, 3, 4) , Claude Kirchner (5) , Catherine Tessier (6)

1 NOS - Numérique, Organisation et Société
2 SES - Département Sciences Economiques et Sociales
3 S2A - Signal, Statistique et Apprentissage
4 IDS - Département Images, Données, Signal
5 Inria - Institut National de Recherche en Informatique et en Automatique
6 DTIS, ONERA, Université de Toulouse [Toulouse]

How to design a facial authentication system taking into account both performance and fairness? We consider the choices that a developer makes when coding such a system, such as the training parameters, the architecture of the neural network or the authentication threshold. We evaluate their impact on the global fairness of the system showing that fairness is not only affected by the training data but also by the multiple choices that are made when coding the model.

Mots clés: TRAITEMENT IMAGE; EQUITÉ; ETHIQUE

Domaines: Intelligence artificielle [cs.AI]

Mélanie Gornet, Claude Kirchner, Catherine Tessier. Operational Fairness for Facial Authentication Systems. 2022. ⟨hal-03837716⟩