Exacerbating Algorithmic Bias through Fairness Attacks
Exacerbating Algorithmic Bias through Fairness Attacks
复制标题
通过公平攻击加剧算法偏差
DOI：
10.1609/aaai.v35i10.17080
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
A. Galstyan
中科院分区：
文献类型：
--
作者：
Ninareh Mehrabi;Muhammad Naveed;Fred Morstatter;A. Galstyan
近年来，算法公平性引起了人们的广泛关注，人们提出了许多定量措施来表征不同机器学习算法的公平性。尽管存在这种兴趣，但这些公平措施针对故意对抗性攻击的稳健性尚未得到适当解决。事实上，大多数对抗性机器学习都关注恶意攻击对系统准确性的影响，而没有考虑系统的公平性。我们提出了新型数据中毒攻击，其中对手故意针对系统的公平性。具体来说，我们提出了两种针对公平措施的攻击。在锚定攻击中，我们通过将中毒点放置在特定目标点附近来扭曲决策边界，从而使结果产生偏差。在对公平性的影响攻击中，我们的目标是最大化敏感属性与决策结果之间的协方差，影响模型的公平性。我们进行了大量的实验来表明我们提出的攻击的有效性。
Algorithmic fairness has attracted significant attention in recent years, with many quantitative measures suggested for characterizing the fairness of different machine learning algorithms. Despite this interest, the robustness of those fairness measures with respect to an intentional adversarial attack has not been properly addressed. Indeed, most adversarial machine learning has focused on the impact of malicious attacks on the accuracy of the system, without any regard to the system's fairness. We propose new types of data poisoning attacks where an adversary intentionally targets the fairness of a system. Specifically, we propose two families of attacks that target fairness measures. In the anchoring attack, we skew the decision boundary by placing poisoned points near specific target points to bias the outcome. In the influence attack on fairness, we aim to maximize the covariance between the sensitive attributes and the decision outcome and affect the fairness of the model. We conduct extensive experiments that indicate the effectiveness of our proposed attacks.
实现数据发布中的非歧视
DOI：
10.1145/3097983.3098167
发表时间：
2017
期刊：
the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD
影响因子：
--
作者：
Zhang, Lu;Wu, Yongkai;Wu, Xintao
通讯作者：
Wu, Xintao
仿生激光技术修复H13模具钢的力学性能
影响因子：
5
作者：
Cong, Dalong;Zhou, Hong;Wang, Chuanwei
通讯作者：
Wang, Chuanwei