The pervasive adoption of Artificial Intelligence (AI) models in the modern information society, requires counterbalancing the growing decision power demanded to AI models with risk assessment methodologies. In this paper, we consider the risk of discriminatory decisions and review approaches for discovering discrimination and for designing fair AI models. We highlight the tight relations between discrimination discovery and explainable AI, with the latter being a more general approach for understanding the behavior of black boxes.
Opening the black box: a primer for anti-discrimination
S. Ruggieri
;R. Guidotti;A. Monreale;D. Pedreschi;F. Turini
2020-01-01
Abstract
The pervasive adoption of Artificial Intelligence (AI) models in the modern information society, requires counterbalancing the growing decision power demanded to AI models with risk assessment methodologies. In this paper, we consider the risk of discriminatory decisions and review approaches for discovering discrimination and for designing fair AI models. We highlight the tight relations between discrimination discovery and explainable AI, with the latter being a more general approach for understanding the behavior of black boxes.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
annuario.pdf
accesso aperto
Descrizione: Articolo principale
Tipologia:
Documento in Pre-print
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
445.44 kB
Formato
Adobe PDF
|
445.44 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.