Constructing Unrestricted Adversarial Examples with Generative Models Constructing Unrestricted Adversarial Examples with Generative Models
Paper summary Song et al. propose generative adversarial examples, crafted using a generative adversarial network (GAN) from scratch. In particular a GAN is trained on the original images in order to approximate the generative data distribution. Then, adversarial examples can be found in the learned latent space by finding a latent code that minimizes a loss consisting of fooling the target classifier, not fooling an auxiliary classifier (to not change the actual class) and (optionally) staying close to some fixed random latent code. These adversarial examples do not correspond ot original images anymore, instead they are unrestricted and computed from scratch. Figure 1 shows examples. https://i.imgur.com/Krr9MuU.png Figure 1: Examples of projected gradient descent (PGD, top) to find adversarial examples in the image space, and found adversarial examples in the latent space, as proposed. Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).
papers.nips.cc
scholar.google.com
Constructing Unrestricted Adversarial Examples with Generative Models
Song, Yang and Shu, Rui and Kushman, Nate and Ermon, Stefano
Neural Information Processing Systems Conference - 2018 via Local Bibsonomy
Keywords: dblp




ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and