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 1806.01477cs.CRcs.LGstat.ML
收藏

一种可解释的深度学习神经网络对抗鲁棒性度量

An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks

Department of Electrical and Computer Engineering, University of Illinois at Chicago(伊利诺伊大学芝加哥分校电气与计算机工程系);Kitware Inc.(Kitware公司);University of Illinois at Chicago(伊利诺伊大学芝加哥分校)

Chirag Agarwal, Bo Dong, Dan Schonfeld, Anthony Hoogs

摘要:

深度神经网络(DNN)通过在各种视觉任务中实现最先进的性能,极大地推进了计算机视觉领域。这些结果不仅限于视觉领域,还可以在语音识别和机器翻译任务中看到。最近,DNN被发现在使用通过对原始输入图像进行不可察觉的更改而制作的样本进行测试时失败率很低。这导致了DNN的验证和对抗性能之间的差距。一个有效的和可推广的鲁棒性指标,用于评估DNN对这些对抗性输入的性能仍然缺乏文献。在本文中,我们提出了噪声敏感度得分(NSS),这是一种量化DNN在不同形式的固定方向攻击下对特定输入的性能的度量。一个有见地的数学解释提供了深入理解所提出的度量。通过利用NSS,我们还提出了一个基于偏度的数据集鲁棒性度量,用于评估DNN在给定数据集上的对抗性能。使用广泛使用的最先进的架构以及流行的分类数据集,如MNIST,CIFAR-10,CIFAR-100和ImageNet,进行了广泛的实验,以验证我们提出的指标的有效性和通用性。与以前的工作不同,所提出的NSS不是简单地测量DNN在输入域中的对抗鲁棒性,而是建立在对对抗攻击的深刻数学理解之上,并对鲁棒性给出了更明确的解释。

英文摘要:

Deep Neural Networks(DNN) have excessively advanced the field of computer vision by achieving state of the art performance in various vision tasks. These results are not limited to the field of vision but can also be seen in speech recognition and machine translation tasks. Recently, DNNs are found to poorly fail when tested with samples that are crafted by making imperceptible changes to the original input images. This causes a gap between the validation and adversarial performance of a DNN. An effective and generalizable robustness metric for evaluating the performance of DNN on these adversarial inputs is still missing from the literature. In this paper, we propose Noise Sensitivity Score (NSS), a metric that quantifies the performance of a DNN on a specific input under different forms of fix-directional attacks. An insightful mathematical explanation is provided for deeply understanding the proposed metric. By leveraging the NSS, we also proposed a skewness based dataset robustness metric for evaluating a DNN's adversarial performance on a given dataset. Extensive experiments using widely used state of the art architectures along with popular classification datasets, such as MNIST, CIFAR-10, CIFAR-100, and ImageNet, are used to validate the effectiveness and generalization of our proposed metrics. Instead of simply measuring a DNN's adversarial robustness in the input domain, as previous works, the proposed NSS is built on top of insightful mathematical understanding of the adversarial attack and gives a more explicit explanation of the robustness.

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。

↑