Interpretable privacy with optimizable utility - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Interpretable privacy with optimizable utility

Résumé

In this position paper, we discuss the problem of specifying privacy requirements for machine learning based systems, in an inter-pretable yet operational way. Explaining privacy-improving technology is a challenging problem, especially when the goal is to construct a system which at the same time is interpretable and has a high performance. In order to address this challenge, we propose to specify privacy requirements as constraints, leaving several options for the concrete implementation of the system open, followed by a constraint optimization approach to achieve an efficient implementation also, next to the interpretable privacy guarantees.
Fichier principal
Vignette du fichier
ipcp.pdf (202.05 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02950994 , version 1 (28-09-2020)

Identifiants

  • HAL Id : hal-02950994 , version 1

Citer

Jan Ramon, Moitree Basu. Interpretable privacy with optimizable utility. ECML PKDD 2020 - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases, Sep 2020, Ghent / Virtual, Belgium. ⟨hal-02950994⟩
217 Consultations
203 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More