Substitute model black box attacks can create adversarial examples for a...
Motivated by the general robustness properties of the 01 loss we propose...
We show that white box adversarial examples do not transfer effectively
...
The 01 loss is robust to outliers and tolerant to noisy data compared to...
Brain MRI images consist of multiple 2D images stacked at consecutive sp...
Automatic identification of brain lesions from magnetic resonance imagin...
Random weights in convolutional neural networks have shown promising res...