Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy
arXiv:2009.06389
Abstract
Deployment of deep learning in different fields and industries is growing day by day due to its performance, which relies on the availability of data and compute. Data is often crowd-sourced and contains sensitive information about its contributors, which leaks into models that are trained on it. To achieve rigorous privacy guarantees, differentially private training mechanisms are used. However, it has recently been shown that differential privacy can exacerbate existing biases in the data and have disparate impacts on the accuracy of different subgroups of data. In this paper, we aim to study these effects within differentially private deep learning. Specifically, we aim to study how different levels of imbalance in the data affect the accuracy and the fairness of the decisions made by the model, given different levels of privacy. We demonstrate that even small imbalances and loose privacy guarantees can cause disparate impacts.
arXiv comment5 pages, 5 figures
References in corpus (14)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Deep Learning with Differential Privacy
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Deep Residual Learning for Image Recognition
- Equality of Opportunity in Supervised Learning
- Renyi Differential Privacy
- Differentially Private Empirical Risk Minimization
- Actionable Recourse in Linear Classification
- Differential Privacy: on the trade-off between Utility and Information Leakage
- Privacy in Deep Learning: A Survey
- Does mitigating ML's impact disparity require treatment disparity?
- Deep Learning with Gaussian Differential Privacy
- Differentially Private Fair Learning
- Fair Decision Making using Privacy-Protected Data