Search Results for author: Yunzhe Xue

Found 7 papers, 6 papers with code

Defending against black-box adversarial attacks with gradient-free trained sign activation neural networks

1 code implementation1 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.

Adversarial Defense

Towards adversarial robustness with 01 loss neural networks

1 code implementation20 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.

On the transferability of adversarial examples between convex and 01 loss models

1 code implementation14 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.

Robust binary classification with the 01 loss

1 code implementation9 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.

Classification General Classification

Image classification and retrieval with random depthwise signed convolutional neural networks

1 code implementation15 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.

Classification General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.