2 code implementations • 12 Feb 2024 • Yunzhe Xue, Usman Roshan
We ask the following question in this study: are 01 loss sign activation neural networks hard to deceive with a popular black box text adversarial attack program called TextFooler?
no code implementations • 9 Dec 2023 • Yunzhe Xue, Olanrewaju Eletta, Justin W. Ady, Nell M. Patel, Advaith Bongu, Usman Roshan
As part of their training all medical students and residents have to pass basic surgical tasks such as knot tying, needle-passing, and suturing.
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.
1 code implementation • 26 May 2019 • Yunzhe Xue, Fadi G. Farhat, Olga Boukrina, A . M. Barrett, Jeffrey R. Binder, Usman W. Roshan, William W. Graves
With all three datasets combined, the current system compared to previous methods also attained a reliably higher cross-validation accuracy.
1 code implementation • 15 Jun 2018 • Yunzhe Xue, Usman Roshan
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.