On the Impact of Multi-dimensional Local Differential Privacy on Fairness - Multidisciplinary Institute in Artificial intelligence - Grenoble Alpes Access content directly
Journal Articles Data Mining and Knowledge Discovery Year : 2024

On the Impact of Multi-dimensional Local Differential Privacy on Fairness

Abstract

Automated decision systems are increasingly used to make consequential decisions in people’s lives. Due to the sensitivity of the manipulated data and the resulting decisions, several ethical concerns need to be addressed for the appropriate use of such technologies, particularly fairness and privacy. Unlike previous work, which focused on centralized differential privacy (DP) or on local DP (LDP) for a single sensitive attribute, in this paper, we examine the impact of LDP in the presence of several sensitive attributes (i.e., multi-dimensional data) on fairness. Detailed empirical analysis on synthetic and benchmark datasets revealed very relevant observations. In particular, (1) multi-dimensional LDP is an efficient approach to reduce disparity, (2) the variant of the multi-dimensional approach of LDP (we employ two variants) matters only at low privacy guarantees (high ), and (3) the true decision distribution has an important effect on which group is more sensitive to the obfuscation. Last, we summarize our findings in the form of recommendations to guide practitioners in adopting effective privacy-preserving practices while maintaining fairness and utility in machine learning applications.
Fichier principal
Vignette du fichier
2312.04404v3.pdf (1013.39 Ko) Télécharger le fichier
Origin Files produced by the author(s)
licence

Dates and versions

hal-04329938 , version 1 (07-12-2023)
hal-04329938 , version 2 (19-06-2024)

Licence

Identifiers

Cite

Karima Makhlouf, Héber Hwang Arcolezi, Sami Zhioua, Ghassen Ben Brahim, Catuscia Palamidessi. On the Impact of Multi-dimensional Local Differential Privacy on Fairness. Data Mining and Knowledge Discovery, 2024, pp.1-24. ⟨10.1007/s10618-024-01031-0⟩. ⟨hal-04329938v2⟩
189 View
82 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More