Understanding the risk factors of learning in adversarial environments

Understanding the risk factors of learning in adversarial environments
复制标题

了解对抗性环境中学习的风险因素

DOI:
10.1145/2046684.2046698
复制
发表时间:
2011
期刊:
--
影响因子:
--
通讯作者:
P. Laskov
P. Laskov
中科院分区:
--
文献类型:
--
作者:
B. Nelson;B. Biggio;P. Laskov

文献摘要

参考文献

被引文献

相似文献

安全应用的学习是一个新兴领域,需要自适应方法,但通过改变对抗行为而变得复杂。传统的学习方法假设数据中存在良性错误,因此可能容易受到对抗性错误的影响。在本文中,我们将对抗性腐败的概念直接纳入学习框架,并推导出一个新的分类器对抗性污染的鲁棒性标准。
Learning for security applications is an emerging field where adaptive approaches are needed but are complicated by changing adversarial behavior. Traditional approaches to learning assume benign errors in data and thus may be vulnerable to adversarial errors. In this paper, we incorporate the notion of adversarial corruption directly into the learning framework and derive a new criteria for classifier robustness to adversarial contamination.
DOI: 10.1016/b978-0-12-386908-1.00037-9
发表时间: 2018-11
期刊: Wiley Series in Probability and Statistics
影响因子: --
作者:
Bruce E. Blaine
通讯作者: Bruce E. Blaine