论文标题
公平感知回归对对抗性攻击的强大
Fairness-aware Regression Robust to Adversarial Attacks
论文作者
论文摘要
在本文中，我们朝着回答如何设计公平机器学习算法的问题迈出的第一步，这些算法对对抗性攻击是可靠的。使用Minimax框架，我们旨在设计一个具有对抗性的公平回归模型，该模型在攻击者的存在下实现最佳性能，该攻击者能够在数据集中添加精心设计的对抗数据点或对数据集执行排名攻击。通过解决提出的非平滑非Convex-nonconcave minimax问题，获得了最佳对手以及强大的公平感知回归模型。对于合成数据和现实数据集，数值结果表明，在预测准确性和基于组的公平度量方面，所提出的对抗性稳健的公平模型在中毒数据集上具有比其他公平机器学习模型更好的性能。
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.
