可解释AI与对抗攻击的易感性：乳腺癌超声图像分类的案例研究
Explainable AI and susceptibility to adversarial attacks: a case study in classification of breast ultrasound images
- Electrical and Computer Engineering（电气与计算机工程系）
- Concordia University（康科迪亚大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文研究乳腺癌超声图像分类中可解释AI的对抗攻击易感性，提出基于ResNet-50的多任务学习网络提升分类准确率，揭示对抗攻击可显著改变重要性图且难以检测。
AI中文摘要：
超声是一种非侵入性成像方式，可方便地用于对可疑乳腺结节进行分类，并潜在地检测乳腺癌的发病。最近，卷积神经网络（CNN）技术在将乳腺超声图像分类为良性或恶性方面显示出令人鼓舞的结果。然而，CNN的推理过程是一个黑盒模型，其决策过程不可解释。因此，越来越多的努力致力于解释这一过程，最显著的是通过GRAD-CAM和其他提供CNN内部工作原理视觉解释的技术。除了解释之外，这些方法还提供了临床重要信息，例如确定活检或治疗的位置。在这项工作中，我们分析了如何设计几乎无法检测的对抗攻击来显著改变这些重要性图。此外，我们将展示这种重要性图的改变可能伴随或不伴随分类结果的改变，使其更难被检测。因此，在使用这些重要性图来揭示深度学习的内部工作原理时必须谨慎。最后，我们利用多任务学习（MTL）并提出了一个基于ResNet-50的新网络来提高分类准确率。我们的敏感性和特异性与最先进的结果相当。
英文摘要：
Ultrasound is a non-invasive imaging modality that can be conveniently used to classify suspicious breast nodules and potentially detect the onset of breast cancer. Recently, Convolutional Neural Networks (CNN) techniques have shown promising results in classifying ultrasound images of the breast into benign or malignant. However, CNN inference acts as a black-box model, and as such, its decision-making is not interpretable. Therefore, increasing effort has been dedicated to explaining this process, most notably through GRAD-CAM and other techniques that provide visual explanations into inner workings of CNNs. In addition to interpretation, these methods provide clinically important information, such as identifying the location for biopsy or treatment. In this work, we analyze how adversarial assaults that are practically undetectable may be devised to alter these importance maps dramatically. Furthermore, we will show that this change in the importance maps can come with or without altering the classification result, rendering them even harder to detect. As such, care must be taken when using these importance maps to shed light on the inner workings of deep learning. Finally, we utilize Multi-Task Learning (MTL) and propose a new network based on ResNet-50 to improve the classification accuracies. Our sensitivity and specificity is comparable to the state of the art results.
