How unfair is private learning ?

2022/06/08 by Amartya Sanyal, Sanyal, Amartya, Yaxi Hu +3 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2206.03985

openalex publication_date 2022/06/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

As machine learning algorithms are deployed on sensitive data in critical decision making processes, it is becoming increasingly important that they are also private and fair. In this paper, we show that, when the data has a long-tailed structure, it is not possible to build accurate learning algorithms that are both private and results in higher accuracy on minority subpopulations. We further show that relaxing overall accuracy can lead to good fairness even with strict privacy requirements. To corroborate our theoretical results in practice, we provide an extensive set of experimental results using a variety of synthetic, vision (CIFAR10 and CelebA), and tabular (Law School) datasets and learning algorithms.

Cited by

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

Related

• On the Privacy Risks of Algorithmic Fairness
• Differentially Private Fair Learning
• Privacy at a Price: Exploring its Dual Impact on AI Fairness
• Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy
• Fairness-Driven Private Collaborative Machine Learning