Passer à la navigation principale Passer à la recherche Passer au contenu principal

A non-discriminatory approach to ethical deep learning

  • University of Turin

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

Résumé

Artificial neural networks perform state-of-the-art in an ever-growing number of tasks, nowadays they are used to solve an incredibly large variety of tasks. However, typical training strategies do not take into account lawful, ethical and discriminatory potential issues the trained ANN models could incur in. In this work we propose NDR, a non-discriminatory regularization strategy to prevent the ANN model to solve the target task using some discriminatory features like, for example, the ethnicity in an image classification task for human faces. In particular, a part of the ANN model is trained to hide the discriminatory information such that the rest of the network focuses in learning the given learning task. Our experiments show that NDR can be exploited to achieve non-discriminatory models with both minimal computational overhead and performance loss.

langue originaleAnglais
titreProceedings - 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2020
rédacteurs en chefGuojun Wang, Ryan Ko, Md Zakirul Alam Bhuiyan, Yi Pan
EditeurInstitute of Electrical and Electronics Engineers Inc.
Pages943-950
Nombre de pages8
ISBN (Electronique)9781665403924
Les DOIs
étatPublié - 1 déc. 2020
Modification externeOui
Evénement19th IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2020 - Guangzhou, Chine
Durée: 29 déc. 20201 janv. 2021

Série de publications

NomProceedings - 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2020

Une conférence

Une conférence19th IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2020
Pays/TerritoireChine
La villeGuangzhou
période29/12/201/01/21

Empreinte digitale

Examiner les sujets de recherche de « A non-discriminatory approach to ethical deep learning ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation