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.

A non-discriminatory approach to ethical deep learning

Tartaglione E.
First
;
Grangetto M.
Last
2020-01-01

Abstract

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.
2020
19th IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2020
chn
2020
Proceedings - 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2020
Institute of Electrical and Electronics Engineers Inc.
943
950
978-073814380-4
https://arxiv.org/abs/2008.01430
Deep learning; Discriminatory features; Edge computing; Ethical learning; Neural networks; Regularization
Tartaglione E.; Grangetto M.
File in questo prodotto:
File Dimensione Formato  
TrustCOM2020.pdf

Accesso aperto

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 455.62 kB
Formato Adobe PDF
455.62 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1780908
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact