论文标题
通过细心的卷积神经网络对抗强大的医疗分类
Adversarially Robust Medical Classification via Attentive Convolutional Neural Networks
论文作者
论文摘要
基于卷积神经网络的医学图像分类器已被证明特别容易受到对抗例子的影响。在自动诊断的未来，这种不稳定性可能是无法接受的。尽管事实证明，统计对抗示例检测方法是有效的防御机制，但需要进行其他研究，以研究基于深度学习的系统的基本脆弱性，以及如何最好地构建共同最大化传统准确性的模型。本文介绍了基于CNN的医学图像分类器中的注意机制，作为一种可靠而有效的策略，可提高稳健精度而无需牺牲。在典型的对抗情况下，这种方法能够提高最多16％，在极端情况下最多可提高2700％。
Convolutional neural network-based medical image classifiers have been shown to be especially susceptible to adversarial examples. Such instabilities are likely to be unacceptable in the future of automated diagnoses. Though statistical adversarial example detection methods have proven to be effective defense mechanisms, additional research is necessary that investigates the fundamental vulnerabilities of deep-learning-based systems and how best to build models that jointly maximize traditional and robust accuracy. This paper presents the inclusion of attention mechanisms in CNN-based medical image classifiers as a reliable and effective strategy for increasing robust accuracy without sacrifice. This method is able to increase robust accuracy by up to 16% in typical adversarial scenarios and up to 2700% in extreme cases.
