arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.07280cs.LGcs.AIstat.ML
收藏

一种能抵抗附着点破坏的有限特征的子空间方法

Subspace Methods That Are Resistant to a Limited Number of Features Corrupted by an Adversary

Perspecta Labs(Perspecta实验室)

Chris Mesterharm, Rauf Izmailov, Scott Alexander, Simon Tsang

摘要:

在本文中,我们考虑批量监督学习,其中允许对手破坏具有任意大噪声的实例。允许攻击者破坏每个实例中的任何$l$功能,并且攻击者可以以任何方式更改其值。这种噪声被引入测试实例,并且算法不会接收到这些实例的标签反馈。我们提供了几个子空间投票技术,可用于改造现有的算法,并证明在这种设置数据相关的性能界限。我们的结果的关键见解是,我们设置我们的参数,使一个显着的部分投票假设不包含腐败的功能,对于许多现实世界的问题,这些不腐败的假设是足以实现高精度。我们经验验证我们的方法在几个数据集,包括三个新的数据集,处理侧通道电磁信息。

英文摘要:

In this paper, we consider batch supervised learning where an adversary is allowed to corrupt instances with arbitrarily large noise. The adversary is allowed to corrupt any $l$ features in each instance and the adversary can change their values in any way. This noise is introduced on test instances and the algorithm receives no label feedback for these instances. We provide several subspace voting techniques that can be used to transform existing algorithms and prove data-dependent performance bounds in this setting. The key insight to our results is that we set our parameters so that a significant fraction of the voting hypotheses do not contain corrupt features and, for many real world problems, these uncorrupt hypotheses are sufficient to achieve high accuracy. We empirically validate our approach on several datasets including three new datasets that deal with side channel electromagnetic information.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑