arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2007.01507cs.LGcs.CRstat.ML
收藏

利用包围网络和噪声层实现鲁棒的深度学习

Towards Robust Deep Learning with Ensemble Networks and Noisy Layers

McMaster University(麦克马斯特大学);Ryerson University(瑞尔森大学);Vector Institute(向量研究所)

Yuting Liang, Reza Samavi

摘要:

在本文中,我们提供了一种用于深度学习的方法,该方法可以在图像分类类型的网络中防止对抗性示例。该方法依赖于两种机制:1)以牺牲准确性为代价来增加鲁棒性的机制,以及2)提高准确性但并不总是增加鲁棒性的机制。我们表明,结合这两种机制的方法可以在保持准确性的同时提供对抗性示例的保护。我们制定潜在的攻击我们的方法与实验结果,以证明其有效性。我们还为我们的方法提供了鲁棒性保证以及对保证的解释。

英文摘要:

In this paper we provide an approach for deep learning that protects against adversarial examples in image classification-type networks. The approach relies on two mechanisms:1) a mechanism that increases robustness at the expense of accuracy, and, 2) a mechanism that improves accuracy but does not always increase robustness. We show that an approach combining the two mechanisms can provide protection against adversarial examples while retaining accuracy. We formulate potential attacks on our approach with experimental results to demonstrate its effectiveness. We also provide a robustness guarantee for our approach along with an interpretation for the guarantee.

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。

↑