# To be Robust and to be Fair: Aligning Fairness with Robustness

arXiv: https://arxiv.org/abs/2304.00061 · HTML: https://mlsanity.com/paper/2304.00061/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 31 Mar 2023.

## Builds on (most cited first, 26 of 26)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [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)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Identifying and Correcting Label Bias in Machine Learning](https://mlsanity.com/paper/1901.04966/) (2019)
- [Learnable Boundary Guided Adversarial Training](https://mlsanity.com/paper/2011.11164/) (2020)
- [Smooth Adversarial Training](https://mlsanity.com/paper/2006.14536/) (2020)
- [Operationalizing Individual Fairness with Pairwise Fair Representations](https://mlsanity.com/paper/1907.01439/) (2019)
- [Poisoning Attacks on Algorithmic Fairness](https://mlsanity.com/paper/2004.07401/) (2020)
- [Fair Feature Distillation for Visual Recognition](https://mlsanity.com/paper/2106.04411/) (2021)
- [Two Simple Ways to Learn Individual Fairness Metrics from Data](https://mlsanity.com/paper/2006.11439/) (2020)
- [Verifying Individual Fairness in Machine Learning Models](https://mlsanity.com/paper/2006.11737/) (2020)
- [Sample Selection for Fair and Robust Training](https://mlsanity.com/paper/2110.14222/) (2021)
- [Exacerbating Algorithmic Bias through Fairness Attacks](https://mlsanity.com/paper/2012.08723/) (2020)
- [Boosting Fast Adversarial Training with Learnable Adversarial Initialization](https://mlsanity.com/paper/2110.05007/) (2021)
- [Understanding Instance-Level Impact of Fairness Constraints](https://mlsanity.com/paper/2206.15437/) (2022)
- [Group-Aware Threshold Adaptation for Fair Classification](https://mlsanity.com/paper/2111.04271/) (2021)

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

- [Causality-Aided Trade-off Analysis for Machine Learning Fairness](https://mlsanity.com/paper/2305.13057/) (2023)
- [Multigroup Robustness](https://mlsanity.com/paper/2405.00614/) (2024)

## Abstract (arXiv)

Adversarial training has been shown to be reliable in improving robustness against adversarial samples. However, the problem of adversarial training in terms of fairness has not yet been properly studied, and the relationship between fairness and accuracy attack still remains unclear. Can we simultaneously improve robustness w.r.t. both fairness and accuracy? To tackle this topic, in this paper, we study the problem of adversarial training and adversarial attack w.r.t. both metrics. We propose a unified structure for fairness attack which brings together common notions in group fairness, and we theoretically prove the equivalence of fairness attack against different notions. Moreover, we show the alignment of fairness and accuracy attack, and theoretically demonstrate that robustness w.r.t. one metric benefits from robustness w.r.t. the other metric. Our study suggests a novel way to unify adversarial training and attack w.r.t. fairness and accuracy, and experimental results show that our proposed method achieves better performance in terms of robustness w.r.t. both metrics.