On the impact of multi-dimensional local differential privacy on fairness

DOI10.1007/S10618-024-01031-0MaRDI QIDQ6609097zbMATH OpenFDO

Authors Karima Makhlouf, Héber H. Arcolezi, Sami Zhioua, Ghassen Ben Brahim, Catuscia Palamidessi

Publication date 20 September 2024

Published in Data Mining and Knowledge Discovery (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10618-024-01031-0

zbMATH Keywords

differential privacyfairnessmachine learningrandomized response

Mathematics Subject Classification ID

Privacy of data (68P27) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Mitigating disparate impact on model accuracy in differentially private learning
• Accuracy and fairness trade-offs in machine learning: a stochastic multi-objective approach
• Causal Fairness Analysis: A Causal Toolkit for Fair Machine Learning
• Enforcing fairness using ensemble of diverse Pareto-optimal models
• Fairness in credit scoring: assessment, implementation and profit implications

Cites work

• Causality. Models, reasoning, and inference
• Fairness through awareness
• Random forests
• Randomized response: a survey technique for eliminating evasive answer bias
• Scikit-learn: machine learning in Python
• The algorithmic foundations of differential privacy
• Theory of Cryptography
• What can we learn privately?

Cited in

(1)

• Mitigating disparate impact on model accuracy in differentially private learning

This page was built for publication: On the impact of multi-dimensional local differential privacy on fairness

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6609097)