paper-with-me

홈 › Papers

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

2023-12-07 · Karima Makhlouf, Heber H. Arcolezi, Sami Zhioua, Ghassen Ben Brahim, Catuscia Palamidessi

Automated decision systems are increasingly used to make consequential decisions in people's lives. Due to the sensitivity of the manipulated data as well as the resulting decisions, several ethical concerns need to be addressed for the appropriate use of such technologies, in particular, fairness and privacy. Unlike previous work, which focused on centralized differential privacy (DP) or 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 multi-dimensional approach of LDP (independent vs. combined) matters only at low privacy guarantees, and (3) the outcome Y 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 ML applications.

📄 PDF Abstract BibTeX arXiv:2312.04404

Code (1)

karimamakhlouf/impact_of_ldp_on_fairness 공식 구현

Tasks

AttributeFairnessPrivacy Preserving

Similar Papers 제목 키워드 기반

Decentralized Differentially Private Power Method

2025-07-30 · Andrew Campbell, Anna Scaglione, Sean Peisert arxiv

We propose a novel Decentralized Differentially Private Power Method (D-DP-PM) for performing Principal Component Analysis (PCA) in networked multi-agent settings. Unlike conventional decentralized PCA approaches where e…

Federated Transfer Learning with Differential Privacy

2024-03-17 · Mengchu Li, Ye Tian, Yang Feng, Yi Yu

Federated learning has emerged as a powerful framework for analysing distributed data, yet two challenges remain pivotal: heterogeneity across sites and privacy of local data. In this paper, we address both challenges wi…

Federated LearningregressionTransfer Learning

Locally Differentially Private Naive Bayes Classification

2019-05-03 · Emre Yilmaz, Mohammad Al-Rubaie, J. Morris Chang

In machine learning, classification models need to be trained in order to predict class labels. When the training data contains personal information about individuals, collecting training data becomes difficult due to pr…

ClassificationDimensionality ReductionGeneral Classification

High-Probability Bounds For Heterogeneous Local Differential Privacy

2025-10-13 · Maryam Aliakbarpour, Alireza Fallah, Swaha Roy, Ria Stevens arxiv

We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation anal…

Differentially Private High Dimensional Bandits

2024-02-06 · Apurv Shukla

We consider a high-dimensional stochastic contextual linear bandit problem when the parameter vector is $s_{0}$-sparse and the decision maker is subject to privacy constraints under both central and local models of diffe…