Exploiting Fairness to Enhance Sensitive Attributes Reconstruction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Exploiting Fairness to Enhance Sensitive Attributes Reconstruction

Résumé

In recent years, a growing body of work has emerged on how to learn machine learning models under fairness constraints, often expressed with respect to some sensitive attributes. In this work, we consider the setting in which an adversary has black-box access to a target model and show that information about this model's fairness can be exploited by the adversary to enhance his reconstruction of the sensitive attributes of the training data. More precisely, we propose a generic reconstruction correction method, which takes as input an initial guess made by the adversary and corrects it to comply with some user-defined constraints (such as the fairness information) while minimizing the changes in the adversary's guess. The proposed method is agnostic to the type of target model, the fairness-aware learning method as well as the auxiliary knowledge of the adversary. To assess the applicability of our approach, we have conducted a thorough experimental evaluation on two state-of-the-art fair learning methods, using four different fairness metrics with a wide range of tolerances and with three datasets of diverse sizes and sensitive attributes. The experimental results demonstrate the effectiveness of the proposed approach to improve the reconstruction of the sensitive attributes of the training set.
Fichier principal
Vignette du fichier
SATML_ExploitingFairnessToEnhanceSensitiveAttributesReconstruction_version_HAL.pdf (1.49 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03766710 , version 1 (01-09-2022)
hal-03766710 , version 2 (25-11-2022)

Identifiants

Citer

Julien Ferry, Ulrich Aïvodji, Sébastien Gambs, Marie-José Huguet, Mohamed Siala. Exploiting Fairness to Enhance Sensitive Attributes Reconstruction. First IEEE Conference on Secure and Trustworthy Machine Learning, Feb 2023, Raleigh, North Carolina, United States. ⟨10.1109/SaTML54575.2023.00012⟩. ⟨hal-03766710v2⟩
170 Consultations
33 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More