# Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning

arXiv: https://arxiv.org/abs/2006.12621 · HTML: https://mlsanity.com/paper/2006.12621/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 30 of 56)

- [Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization](https://mlsanity.com/paper/2105.05612/) (2021)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [Diagnosing failures of fairness transfer across distribution shift in real-world medical settings](https://mlsanity.com/paper/2202.01034/) (2022)
- [Evaluating Robustness of Counterfactual Explanations](https://mlsanity.com/paper/2103.02354/) (2021)
- [Analysis and Applications of Class-wise Robustness in Adversarial Training](https://mlsanity.com/paper/2105.14240/) (2021)
- [Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition](https://mlsanity.com/paper/2210.09943/) (2022)
- [Speech Robust Bench: A Robustness Benchmark For Speech Recognition](https://mlsanity.com/paper/2403.07937/) (2024)
- [Technical Challenges for Training Fair Neural Networks](https://mlsanity.com/paper/2102.06764/) (2021)
- [Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification](https://mlsanity.com/paper/2106.10826/) (2021)
- [The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification](https://mlsanity.com/paper/2105.02778/) (2021)
- [On Catastrophic Inheritance of Large Foundation Models](https://mlsanity.com/paper/2402.01909/) (2024)
- [FairCanary: Rapid Continuous Explainable Fairness](https://mlsanity.com/paper/2106.07057/) (2021)
- [Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks](https://mlsanity.com/paper/2209.05957/) (2022)
- [Robustness Disparities in Commercial Face Detection](https://mlsanity.com/paper/2108.12508/) (2021)
- [Fair SA: Sensitivity Analysis for Fairness in Face Recognition](https://mlsanity.com/paper/2202.03586/) (2022)
- [Fairness Properties of Face Recognition and Obfuscation Systems](https://mlsanity.com/paper/2108.02707/) (2021)
- [Understanding the Impact of Adversarial Robustness on Accuracy Disparity](https://mlsanity.com/paper/2211.15762/) (2022)
- [Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools](https://mlsanity.com/paper/2309.17337/) (2023)
- [DRoP: Distributionally Robust Data Pruning](https://mlsanity.com/paper/2404.05579/) (2024)
- [Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond](https://mlsanity.com/paper/2503.07501/) (2025)
- [Fairness Degrading Adversarial Attacks Against Clustering Algorithms](https://mlsanity.com/paper/2110.12020/) (2021)
- [Subverting Fair Image Search with Generative Adversarial Perturbations](https://mlsanity.com/paper/2205.02414/) (2022)
- [Fairness Increases Adversarial Vulnerability](https://mlsanity.com/paper/2211.11835/) (2022)
- [Robustness Disparities in Face Detection](https://mlsanity.com/paper/2211.15937/) (2022)
- [Fairness and Sequential Decision Making: Limits, Lessons, and Opportunities](https://mlsanity.com/paper/2301.05753/) (2023)
- [Diffused Redundancy in Pre-trained Representations](https://mlsanity.com/paper/2306.00183/) (2023)
- [Trustworthy AI Must Account for Interactions](https://mlsanity.com/paper/2504.07170/) (2025)
- [FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networks](https://mlsanity.com/paper/2206.00553/) (2022)
- [Fairness-aware Regression Robust to Adversarial Attacks](https://mlsanity.com/paper/2211.04449/) (2022)
- [Characterizing Data Point Vulnerability via Average-Case Robustness](https://mlsanity.com/paper/2307.13885/) (2023)

## Abstract (arXiv)

Deep neural networks (DNNs) are increasingly used in real-world applications (e.g. facial recognition). This has resulted in concerns about the fairness of decisions made by these models. Various notions and measures of fairness have been proposed to ensure that a decision-making system does not disproportionately harm (or benefit) particular subgroups of the population. In this paper, we argue that traditional notions of fairness that are only based on models' outputs are not sufficient when the model is vulnerable to adversarial attacks. We argue that in some cases, it may be easier for an attacker to target a particular subgroup, resulting in a form of textitrobustness bias. We show that measuring robustness bias is a challenging task for DNNs and propose two methods to measure this form of bias. We then conduct an empirical study on state-of-the-art neural networks on commonly used real-world datasets such as CIFAR-10, CIFAR-100, Adience, and UTKFace and show that in almost all cases there are subgroups (in some cases based on sensitive attributes like race, gender, etc) which are less robust and are thus at a disadvantage. We argue that this kind of bias arises due to both the data distribution and the highly complex nature of the learned decision boundary in the case of DNNs, thus making mitigation of such biases a non-trivial task. Our results show that robustness bias is an important criterion to consider while auditing real-world systems that rely on DNNs for decision making. Code to reproduce all our results can be found here: urlhttps://github.com/nvedant07/Fairness-Through-Robustness