Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey
arXiv:2202.08187 · doi:10.24963/ijcai.2022/766
Abstract
This paper surveys recent work in the intersection of differential privacy (DP) and fairness. It reviews the conditions under which privacy and fairness may have aligned or contrasting goals, analyzes how and why DP may exacerbate bias and unfairness in decision problems and learning tasks, and describes available mitigation measures for the fairness issues arising in DP systems. The survey provides a unified understanding of the main challenges and potential risks arising when deploying privacy-preserving machine-learning or decisions-making tasks under a fairness lens.
arXiv commentAdded research funding support and conference venue
References in corpus (12)
- Deep Learning with Differential Privacy
- Equality of Opportunity in Supervised Learning
- Scalable Private Learning with PATE
- Functional Mechanism: Regression Analysis under Differential Privacy
- Mitigating Bias in Federated Learning
- Fair Learning with Private Demographic Data
- Differential Privacy of Hierarchical Census Data: An Optimization Approach
- Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings
- A Fairness Analysis on Private Aggregation of Teacher Ensembles
- Improving Fairness and Privacy in Selection Problems
- Observations on the Bias of Nonnegative Mechanisms for Differential Privacy
- Post-processing of Differentially Private Data: A Fairness Perspective