Adaptive Adversarial Training Does Not Increase Recourse Costs
Adaptive Adversarial Training Does Not Increase Recourse Costs
复制标题
自适应对抗训练不会增加资源成本
DOI：
10.1145/3600211.3604704
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Liu, Yang
中科院分区：
文献类型：
--
作者：
Hardy, Ian;Yetukuri, Jayanth;Liu, Yang
Recent work has connected adversarial attack methods and algorithmic recourse methods: both seek minimal changes to an input instance which alter a model’s classification decision. It has been shown that traditional adversarial training, which seeks to minimize a classifier’s susceptibility to malicious perturbations, increases the cost of generated recourse; with larger adversarial training radii correlating with higher recourse costs. From the perspective of algorithmic recourse, however, the appropriate adversarial training radius has always been unknown. Another recent line of work has motivated adversarial training with adaptive training radii to address the issue of instance-wise variable adversarial vulnerability, showing success in domains with unknown attack radii. This work studies the effects of adaptive adversarial training on algorithmic recourse costs. We establish that the improvements in model robustness induced by adaptive adversarial training show little effect on algorithmic recourse costs, providing a potential avenue for affordable robustness in domains where recoursability is critical.
登录
查看更多内容
DOI：
--
发表时间：
2021-06
期刊：
--
影响因子：
--
作者：
Martin Pawelczyk;Chirag Agarwal;Shalmali Joshi;Sohini Upadhyay;Himabindu Lakkaraju
通讯作者：
Martin Pawelczyk;Chirag Agarwal;Shalmali Joshi;Sohini Upadhyay;Himabindu Lakkaraju
DOI：
10.1145/3351095.3372876
发表时间：
2020-01
期刊：
Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
影响因子：
--
作者：
S. Venkatasubramanian;M. Alfano
通讯作者：
S. Venkatasubramanian;M. Alfano
DOI：
10.1145/3366423.3380087
发表时间：
2019-10
期刊：
Proceedings of The Web Conference 2020
影响因子：
--
作者：
Martin Pawelczyk;Klaus Broelemann;Gjergji Kasneci
通讯作者：
Martin Pawelczyk;Klaus Broelemann;Gjergji Kasneci
利用深度学习和海运物流大数据预测航运市场状况的研究
DOI：
--
发表时间：
2019
期刊：
影响因子：
--
作者：
和田 祐次郎;河原 大輝;濱田 邦裕
通讯作者：
濱田 邦裕
表格数据反事实生成方法的框架和基准研究
影响因子：
--
作者：
Raphael Mazzine;David Martens
通讯作者：
David Martens