Gradient-based adversarial attacks on deep neural networks pose a serious threat, since they can be deployed by adding imperceptible perturbations to the test data of any network, and the risk they introduce cannot be assessed through the network's original training performance. Denoising and dimensionality reduction are two distinct methods that have been independently investigated to combat such attacks. While denoising offers the ability to tailor the defense to the specific nature of the attack, dimensionality reduction offers the advantage of potentially removing previously unseen perturbations, along with reducing the training time of the network being defended. We propose strategies to combine the advantages of these two defense mechanisms. First, we propose the cascaded defense, which involves denoising followed by dimensionality reduction. To reduce the training time of the defense for a small trade-off in performance, we propose the hidden layer defense, which involves feeding the output of the encoder of a denoising autoencoder into the network. Further, we discuss how adaptive attacks against these defenses could become significantly weak when an alternative defense is used, or when no defense is used. In this light, we propose a new metric to evaluate a defense which measures the sensitivity of the adaptive attack to modifications in the defense. Finally, we present a guideline for building an ordered repertoire of defenses, a.k.a. a defense infrastructure, that adjusts to limited computational resources in presence of uncertainty about the attack strategy.


翻译:对深心神经网络的激烈对抗性攻击构成了严重的威胁,因为这些攻击可以通过在任何网络的测试数据中增加无法察觉的干扰来部署,而它们所带来的风险无法通过网络最初的培训性表现来评估。低度和维度减少是两种不同的方法,已经独立调查过,以打击这种攻击。虽然去度减少提供了使防御适应攻击具体性质的能力,但减少维度提供了可能消除以前所见的扰动的优势,同时减少了网络防御的培训时间。我们提出了将这两个防御机制的优势结合起来的战略。首先,我们提出了分层防御,这涉及到分层防御,这涉及到分层防御之后的分层降低。为了减少防御性小规模交易,我们提出了隐藏的层防御,这涉及到将一个分层化的自动化自动化自动电离心器的输出纳入网络。此外,我们讨论了在使用替代防御时,或者在不使用防御时,对这些防御机制的好处会变得非常薄弱。首先,我们提出了分层防御的分层防御战略。最后,我们提议了一种调整防御的弹性防御战略。我们提出了一个新的标准,用来调整了国防的防御结构。为了调整。我们现在的防御的防御结构的调整。我们提出了一个新的标准,一个调整了一种调整。

0
下载
关闭预览

相关内容

【干货书】机器学习速查手册,135页pdf
专知会员服务
123+阅读 · 2020年11月20日
专知会员服务
44+阅读 · 2020年10月31日
【Google】平滑对抗训练,Smooth Adversarial Training
专知会员服务
47+阅读 · 2020年7月4日
强化学习最新教程,17页pdf
专知会员服务
171+阅读 · 2019年10月11日
已删除
将门创投
7+阅读 · 2019年10月10日
Arxiv
12+阅读 · 2020年12月10日
Deflecting Adversarial Attacks
Arxiv
8+阅读 · 2020年2月18日
Adversarial Metric Attack for Person Re-identification
Arxiv
7+阅读 · 2018年6月8日
Arxiv
9+阅读 · 2018年1月4日
VIP会员
相关资讯
已删除
将门创投
7+阅读 · 2019年10月10日
相关论文
Top
微信扫码咨询专知VIP会员