# Regulation Games for Trustworthy Machine Learning

arXiv: https://arxiv.org/abs/2402.03540 · HTML: https://mlsanity.com/paper/2402.03540/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 24 of 24)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Differentially Private Learning Needs Better Features (or Much More Data)](https://mlsanity.com/paper/2011.11660/) (2020)
- [On the Privacy Risks of Algorithmic Fairness](https://mlsanity.com/paper/2011.03731/) (2020)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements](https://mlsanity.com/paper/1901.04562/) (2019)
- [Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy](https://mlsanity.com/paper/2009.06389/) (2020)
- [Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach](https://mlsanity.com/paper/2009.12562/) (2020)
- [Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems](https://mlsanity.com/paper/1806.07552/) (2018)
- [Multi-Objective Multi-Agent Decision Making: A Utility-based Analysis and Survey](https://mlsanity.com/paper/1909.02964/) (2019)
- [Fair Learning with Private Demographic Data](https://mlsanity.com/paper/2002.11651/) (2020)
- [Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings](https://mlsanity.com/paper/2010.06667/) (2020)
- [Disparate Impact in Differential Privacy from Gradient Misalignment](https://mlsanity.com/paper/2206.07737/) (2022)
- [Understanding Fairness of Gender Classification Algorithms Across Gender-Race Groups](https://mlsanity.com/paper/2009.11491/) (2020)
- [Property Testing for Differential Privacy](https://mlsanity.com/paper/1806.06427/) (2018)
- [Automatic Discovery of Privacy-Utility Pareto Fronts](https://mlsanity.com/paper/1905.10862/) (2019)
- [Optimally Deceiving a Learning Leader in Stackelberg Games](https://mlsanity.com/paper/2006.06566/) (2020)
- [Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility](https://mlsanity.com/paper/2302.09183/) (2023)

## Built on by (most cited first, 3 of 3)

- [Exploratory Models of Human-AI Teams: Leveraging Human Digital Twins to Investigate Trust Development](https://mlsanity.com/paper/2411.01049/) (2024)
- [Combining Machine Learning Defenses without Conflicts](https://mlsanity.com/paper/2411.09776/) (2024)
- [Auction-Based Regulation for Artificial Intelligence](https://mlsanity.com/paper/2410.01871/) (2024)

## Abstract (arXiv)

Existing work on trustworthy machine learning (ML) often concentrates on individual aspects of trust, such as fairness or privacy. Additionally, many techniques overlook the distinction between those who train ML models and those responsible for assessing their trustworthiness. To address these issues, we propose a framework that views trustworthy ML as a multi-objective multi-agent optimization problem. This naturally lends itself to a game-theoretic formulation we call regulation games. We illustrate a particular game instance, the SpecGame in which we model the relationship between an ML model builder and fairness and privacy regulators. Regulators wish to design penalties that enforce compliance with their specification, but do not want to discourage builders from participation. Seeking such socially optimal (i.e., efficient for all agents) solutions to the game, we introduce ParetoPlay. This novel equilibrium search algorithm ensures that agents remain on the Pareto frontier of their objectives and avoids the inefficiencies of other equilibria. Simulating SpecGame through ParetoPlay can provide policy guidance for ML Regulation. For instance, we show that for a gender classification application, regulators can enforce a differential privacy budget that is on average 4.0 lower if they take the initiative to specify their desired guarantee first.