# Automated discovery of trade-off between utility, privacy and fairness in machine learning models

arXiv: https://arxiv.org/abs/2311.15691 · HTML: https://mlsanity.com/paper/2311.15691/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 68 references that are in the map.
- First posted on arXiv 27 Nov 2023.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences](https://mlsanity.com/paper/1807.01647/) (2018)
- [Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020](https://mlsanity.com/paper/2104.10201/) (2021)
- [On the Privacy Risks of Algorithmic Fairness](https://mlsanity.com/paper/2011.03731/) (2020)
- [On Formalizing Fairness in Prediction with Machine Learning](https://mlsanity.com/paper/1710.03184/) (2017)
- [Fair Decision Making using Privacy-Protected Data](https://mlsanity.com/paper/1905.12744/) (2019)
- [Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey](https://mlsanity.com/paper/2202.08187/) (2022)
- [On the Convergence and Calibration of Deep Learning with Differential Privacy](https://mlsanity.com/paper/2106.07830/) (2021)
- [Trading Off Privacy, Utility and Efficiency in Federated Learning](https://mlsanity.com/paper/2209.00230/) (2022)
- [Investigating Trade-offs in Utility, Fairness and Differential Privacy in Neural Networks](https://mlsanity.com/paper/2102.05975/) (2021)
- [Automatic Discovery of Privacy-Utility Pareto Fronts](https://mlsanity.com/paper/1905.10862/) (2019)
- [FaiR-N: Fair and Robust Neural Networks for Structured Data](https://mlsanity.com/paper/2010.06113/) (2020)
- [FAIR: Fair Adversarial Instance Re-weighting](https://mlsanity.com/paper/2011.07495/) (2020)
- [An Economic Analysis of Privacy Protection and Statistical Accuracy as Social Choices](https://mlsanity.com/paper/1808.06303/) (2018)
- [End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning](https://mlsanity.com/paper/2104.02532/) (2021)
- [Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design](https://mlsanity.com/paper/2111.14924/) (2021)
- [A penalisation method for batch multi-objective Bayesian optimisation with application in heat exchanger design](https://mlsanity.com/paper/2206.13326/) (2022)
- [(Local) Differential Privacy has NO Disparate Impact on Fairness](https://mlsanity.com/paper/2304.12845/) (2023)
- [Evaluating Differentially Private Machine Learning in Practice](https://mlsanity.com/paper/1902.08874/) (2019)

## Built on by (most cited first, 2 of 2)

- [On the Impact of Multi-dimensional Local Differential Privacy on Fairness](https://mlsanity.com/paper/2312.04404/) (2023)
- [Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems](https://mlsanity.com/paper/2605.24458/) (2026)

## Abstract (arXiv)

Machine learning models are deployed as a central component in decision making and policy operations with direct impact on individuals' lives. In order to act ethically and comply with government regulations, these models need to make fair decisions and protect the users' privacy. However, such requirements can come with decrease in models' performance compared to their potentially biased, privacy-leaking counterparts. Thus the trade-off between fairness, privacy and performance of ML models emerges, and practitioners need a way of quantifying this trade-off to enable deployment decisions. In this work we interpret this trade-off as a multi-objective optimization problem, and propose PFairDP, a pipeline that uses Bayesian optimization for discovery of Pareto-optimal points between fairness, privacy and utility of ML models. We show how PFairDP can be used to replicate known results that were achieved through manual constraint setting process. We further demonstrate effectiveness of PFairDP with experiments on multiple models and datasets.