论文标题
关于跨教学和对抗性示例深度学习表征的相似性
On the Similarity of Deep Learning Representations Across Didactic and Adversarial Examples
论文作者
论文摘要
深度神经网络（DNN）的使用日益促进了一项平行努力：从成功的错误分类中获利的对手的设计。但是，并非所有的对抗例子都是出于恶意目的而设计的。例如，现实世界系统通常包含整个仪器的物理，时间和采样可变性。野外的对抗例子可能会无意中被证明是有害的，以确保准确的预测建模。相反，图像特征的自然发生协方差可能具有教学目的。在这里，我们研究了深度学习表征的稳定性，用于在MRI获取变异性的教学和对抗条件的特征上进行神经影像学分类。我们表明，代表性相似性和性能根据输入空间中对抗示例的频率而有所不同。
The increasing use of deep neural networks (DNNs) has motivated a parallel endeavor: the design of adversaries that profit from successful misclassifications. However, not all adversarial examples are crafted for malicious purposes. For example, real world systems often contain physical, temporal, and sampling variability across instrumentation. Adversarial examples in the wild may inadvertently prove deleterious for accurate predictive modeling. Conversely, naturally occurring covariance of image features may serve didactic purposes. Here, we studied the stability of deep learning representations for neuroimaging classification across didactic and adversarial conditions characteristic of MRI acquisition variability. We show that representational similarity and performance vary according to the frequency of adversarial examples in the input space.
