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 1909.05095cs.LGstat.ML
收藏

深度学习架构的结构鲁棒性

Structural Robustness for Deep Learning Architectures

Université de Montréal(蒙特利尔大学);Mila(米拉研究所);IMT Atlantique(大西洋国立高等工业技术与矿业学校);HEC Montréal(蒙特利尔高等商学院);University of Southern California(南加州大学)

Carlos Lassance, Vincent Gripon, Jian Tang, Antonio Ortega

摘要:

深度网络已被证明在许多机器学习挑战中提供最先进的性能。不幸的是,它们容易受到各种类型的噪声的影响,包括对抗攻击和损坏的输入。在这项工作中,我们引入了一个正式的定义的鲁棒性,它可以被看作是一个本地化的Lipschitz常数的网络功能,量化的域中的数据进行分类。我们比较现有的鲁棒性的概念,并研究其与文献中的方法的连接。我们通过在各种竞争性视觉数据集上进行实验来评估这个指标。

英文摘要:

Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges. Unfortunately, they are susceptible to various types of noise, including adversarial attacks and corrupted inputs. In this work we introduce a formal definition of robustness which can be viewed as a localized Lipschitz constant of the network function, quantified in the domain of the data to be classified. We compare this notion of robustness to existing ones, and study its connections with methods in the literature. We evaluate this metric by performing experiments on various competitive vision datasets.

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。

↑