The non-transferability in our ensemble also makes it a powerful defense to substitute model black box attacks that we show require a much greater distortion than binary and full precision networks to bring our model to zero adversarial accuracy.
To further validate these results we subject all models to substitute model black box attacks under different distortion thresholds and find that the 01 loss network is the hardest to attack across all distortions.
Indeed we see on MNIST that adversaries transfer between 01 loss and convex models more easily than on CIFAR10 and ImageNet which are likely to contain outliers.
We show our algorithms to be fast and comparable in accuracy to the linear support vector machine and logistic loss single hidden layer network for binary classification on several image benchmarks, thus establishing that our method is on-par in test accuracy with convex losses.
We propose a fully 3D multi-path convolutional network to predict stroke lesions from 3D brain MRI images.
With all three datasets combined, the current system compared to previous methods also attained a reliably higher cross-validation accuracy.
We find that k-nearest neighbor gives a comparable precision on the Corel Princeton Image Similarity Benchmark than if we were to use the final layer of trained networks.