Poisoning Attacks on Fair Machine Learning

Poisoning Attacks on Fair Machine Learning
复制标题

对公平机器学习的中毒攻击

DOI:
10.1007/978-3-031-00123-9_30
复制
发表时间:
2022
期刊:
International Conference on Database Systems for Advanced Applications (DASFAA'22
影响因子:
--
通讯作者:
Lu, Aidong
Lu, Aidong
中科院分区:
--
文献类型:
--
作者:
Van, Minh-Hao;Du, Wei Du;Wu, Xintao;Lu, Aidong

文献摘要

参考文献

被引文献

相似文献

公平机器学习和对抗学习都得到了广泛的研究。然而,攻击公平的机器学习模型受到的关注较少。在本文中,我们提出了一个框架,旨在有效地生成中毒样本,以攻击模型准确性和算法公平性。我们的攻击框架可以针对使用各种基于群体的公平概念(如人口均等和均等几率)训练的公平机器学习模型。我们开发了三种在线攻击,对抗性采样,对抗性标记和对抗性特征修改。所有三种攻击都通过采样、标记或修改一小部分训练数据来有效地产生中毒样本,以降低测试准确性。我们的框架使攻击者能够灵活调整攻击的重点在预测准确性或公平性,并准确量化每个候选点对准确性损失和公平性违反的影响,从而产生有效的中毒样本。在两个真实数据集上的实验证明了该框架的有效性和高效性。
Both fair machine learning and adversarial learning have been extensively studied. However, attacking fair machine learning models has received less attention. In this paper, we present a framework that seeks to effectively generate poisoning samples to attack both model accuracy and algorithmic fairness. Our attacking framework can target fair machine learning models trained with a variety of group based fairness notions such as demographic parity and equalized odds. We develop three online attacks, adversarial sampling, adversarial labeling, and adversarial feature modification. All three attacks effectively and efficiently produce poisoning samples via sampling, labeling, or modifying a fraction of training data in order to reduce the test accuracy. Our framework enables attackers to flexibly adjust the attack’s focus on prediction accuracy or fairness and accurately quantify the impact of each candidate point to both accuracy loss and fairness violation, thus producing effective poisoning samples. Experiments on two real datasets demonstrate the effectiveness and efficiency of our framework.
DOI: 10.1609/aaai.v35i10.17080
发表时间: 2020
期刊: ArXiv
影响因子: --
作者:
Ninareh Mehrabi;Muhammad Naveed;Fred Morstatter;A. Galstyan
通讯作者: A. Galstyan
PC-Fairness:衡量基于因果关系的公平性的统一框架
DOI: --
发表时间: 2019
期刊: NeurIPS 2019
影响因子: --
作者:
Wu, Yongkai;Zhang, Lu;Wu, Xintao;Tong, Hanghang
通讯作者: Tong, Hanghang
DOI: --
发表时间: 2020-07
期刊: ArXiv
影响因子: --
作者:
Bahar Taşkesen;Viet Anh Nguyen;D. Kuhn;J. Blanchet
通讯作者: Bahar Taşkesen;Viet Anh Nguyen;D. Kuhn;J. Blanchet
DOI: 10.1109/tnnls.2018.2886017
发表时间: 2019-09-01
影响因子: 10.4
作者:
Yu, Xiaoyong;He, Pan;Li, Xiaolin
通讯作者: Li, Xiaolin