1 code implementation • 1 Jan 2021 • Yunzhe Xue, Meiyan Xie, Zhibo Yang, Usman Roshan
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.
1 code implementation • 20 Aug 2020 • Yunzhe Xue, Meiyan Xie, Usman Roshan
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.
1 code implementation • 14 Jun 2020 • Yunzhe Xue, Meiyan Xie, Usman Roshan
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.
1 code implementation • 9 Feb 2020 • Yunzhe Xue, Meiyan Xie, Usman Roshan
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.
no code implementations • 17 Jul 2019 • Yunzhe Xue, Meiyan Xie, Fadi G. Farhat, Olga Boukrina, A . M. Barrett, Jeffrey R. Binder, Usman W. Roshan, William W. Graves
We propose a fully 3D multi-path convolutional network to predict stroke lesions from 3D brain MRI images.