On the Duality of Privacy and Fairness - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

On the Duality of Privacy and Fairness

Résumé

When a machine learning model operates over data about individuals, there are two common concerns. On one hand, if the model's output (i.e., its prediction) allows for information inferences about an individual's sensitive attributes, we have a privacy issue. On the other hand, if the individual's sensitive attributes can unduly influence the model's output, we have a fairness issue. Recently, the interplay between these two concerns has gathered growing attention both in the scientific community and in society as a whole. In this work, we extend the framework of quantitative information flow to formally capture fairness and privacy as duals of each other, and give first steps toward a novel characterization of their relationship.

Mots clés

Fichier principal
Vignette du fichier
CADE_2023___On_the_Duality_of_Privacy_and_Fairness__Extended_Abstract_.pdf (324.55 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04407491 , version 1 (20-01-2024)

Identifiants

  • HAL Id : hal-04407491 , version 1

Citer

Mário S. Alvim, Natasha Fernandes, Bruno D Nogueira, Catuscia Palamidessi, Thiago V A Silva. On the Duality of Privacy and Fairness. CADE 2023 - International Conference on AI and the Digital Economy, Jun 2023, Venice, Italy. p. 46 - 48. ⟨hal-04407491⟩
20 Consultations
13 Téléchargements

Partager

Gmail Facebook X LinkedIn More