Maximal Jacobian-based Saliency Map Attack

no code implementations • 23 Aug 2018 • Rey Wiyatno, Anqi Xu

The Jacobian-based Saliency Map Attack is a family of adversarial attack methods for fooling classification models, such as deep neural networks for image classification tasks.

Adversarial Attack Classification +2

Style Memory: Making a Classifier Network Generative

no code implementations • ICLR 2018 • Rey Wiyatno, Jeff Orchard

We introduce a network that has the capacity to do both classification and reconstruction by adding a "style memory" to the output layer of the network.

Classification General Classification