Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Say, Lilian, Denis, Christophe, Pinot, Rafael
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917100716556288
author Say, Lilian
Denis, Christophe
Pinot, Rafael
author_facet Say, Lilian
Denis, Christophe
Pinot, Rafael
contents The increasing use of machine learning in sensitive applications demands algorithms that simultaneously preserve data privacy and ensure fairness across potentially sensitive sub-populations. While privacy and fairness have each been extensively studied, their joint treatment remains poorly understood. Existing research often frames them as conflicting objectives, with multiple studies suggesting that strong privacy notions such as differential privacy inevitably compromise fairness. In this work, we challenge that perspective by showing that differential privacy can be integrated into a fairness-enhancing pipeline with minimal impact on fairness guarantees. We design a postprocessing algorithm, called DP2DP, that enforces both demographic parity and differential privacy. Our analysis reveals that our algorithm converges towards its demographic parity objective at essentially the same rate (up logarithmic factor) as the best non-private methods from the literature. Experiments on both synthetic and real datasets confirm our theoretical results, showing that the proposed algorithm achieves state-of-the-art accuracy/fairness/privacy trade-offs.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification
Say, Lilian
Denis, Christophe
Pinot, Rafael
Machine Learning
The increasing use of machine learning in sensitive applications demands algorithms that simultaneously preserve data privacy and ensure fairness across potentially sensitive sub-populations. While privacy and fairness have each been extensively studied, their joint treatment remains poorly understood. Existing research often frames them as conflicting objectives, with multiple studies suggesting that strong privacy notions such as differential privacy inevitably compromise fairness. In this work, we challenge that perspective by showing that differential privacy can be integrated into a fairness-enhancing pipeline with minimal impact on fairness guarantees. We design a postprocessing algorithm, called DP2DP, that enforces both demographic parity and differential privacy. Our analysis reveals that our algorithm converges towards its demographic parity objective at essentially the same rate (up logarithmic factor) as the best non-private methods from the literature. Experiments on both synthetic and real datasets confirm our theoretical results, showing that the proposed algorithm achieves state-of-the-art accuracy/fairness/privacy trade-offs.
title Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification
topic Machine Learning
url https://arxiv.org/abs/2511.18876