mlsanityData to 7 Oct 2026

Fairness-aware Regression Robust to Adversarial Attacks

arXiv 2211.04449 ↗First posted 4 Nov 2022cs.CR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we take a first step towards answering the question of how to design fair machine learning algorithms that are robust to adversarial attacks. Using a minimax framework, we aim to design an adversarially robust fair regression model that achieves optimal performance in the presence of an attacker who is able to add a carefully designed adversarial data point to the dataset or perform a rank-one attack on the dataset. By solving the proposed nonsmooth nonconvex-nonconcave minimax problem, the optimal adversary as well as the robust fairness-aware regression model are obtained. For both synthetic data and real-world datasets, numerical results illustrate that the proposed adversarially robust fair models have better performance on poisoned datasets than other fair machine learning models in both prediction accuracy and group-based fairness measure.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 4 Nov 2022.

Builds on

35 of 51 references.

References · 35

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  4. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  5. 2016Adversarial Machine Learning at Scalecited by 934
  6. 2014Certifying and removing disparate impactcited by 715
  7. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  8. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  9. 2019On Gradient Descent Ascent for Nonconvex-Concave Minimax Problemscited by 266
  10. 2019Fair Regression: Quantitative Definitions and Reduction-based Algorithmscited by 168
  11. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 152
  12. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
23 more
  1. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  2. 2020Fair Regression with Wasserstein Barycenterscited by 99
  3. 2020Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimizationcited by 94
  4. 2018Achieving Fairness through Adversarial Learning: an Application to Recidivism Predictioncited by 77
  5. 2021Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problemscited by 61
  6. 2020Poisoning Attacks on Algorithmic Fairnesscited by 58
  7. 2019Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applicationscited by 55
  8. 2020Fairness Through Robustness: Investigating Robustness Disparity in Deep Learningcited by 55
  9. 2020FR-Train: A Mutual Information-Based Approach to Fair and Robust Trainingcited by 52
  10. 2021Sample Selection for Fair and Robust Trainingcited by 48
  11. 2020Exacerbating Algorithmic Bias through Fairness Attackscited by 47
  12. 2017Fair Kernel Learningcited by 39
  13. 2020On Adversarial Bias and the Robustness of Fair Machine Learningcited by 36
  14. 2021Selective Regression Under Fairness Criteriacited by 34
  15. 2018First-order Convergence Theory for Weakly-Convex-Weakly-Concave Min-max Problemscited by 33
  16. 2021Analysis and Applications of Class-wise Robustness in Adversarial Trainingcited by 33
  17. 2021Poisoning Attacks on Fair Machine Learningcited by 19
  18. 2021Understanding and Mitigating Accuracy Disparity in Regressioncited by 17
  19. 2021Nonconvex-Nonconcave Min-Max Optimization with a Small Maximization Domaincited by 8
  20. 2020Fair Principal Component Analysis and Filter Designcited by 6
  21. 2022Optimality conditions for nonsmooth nonconvex-nonconcave min-max problems and generative adversarial networkscited by 5
  22. 2016Consensus-ADMM for General Quadratically Constrained Quadratic Programmingcited by 3
  23. 2020Optimal Feature Manipulation Attacks Against Linear Regressioncited by 2

Built on by

Cited by year

Citing papers per year: 2024: 4.

4 papers.

  1. 2024Multiple Greedy Quasi-Newton Methods for Saddle Point Problemscited by 3
  2. 2024Diffusion Stochastic Optimization for Min-Max Problemscited by 2
  3. 2024Multigroup Robustnesscited by 2
  4. 2024Auditing and Enforcing Conditional Fairness via Optimal Transportcited by 1