Adversarial Transformation Networks: Learning to Generate Adversarial Examples

@article{Baluja2017AdversarialTN,
  title={Adversarial Transformation Networks: Learning to Generate Adversarial Examples},
  author={Shumeet Baluja and Ian Fischer},
  journal={CoRR},
  year={2017},
  volume={abs/1703.09387}
}

• Shumeet Baluja, Ian Fischer
• Published 2017 in ArXiv

Multiple different approaches of generating adversarial examples have been proposed to attack deep neural networks. These approaches involve either directly computing gradients with respect to the image pixels, or directly solving an optimization on the image pixels. In this work, we present a fundamentally new method for generating adversarial examples that is fast to execute and provides exceptional diversity of output. We efficiently train feed-forward neural networks in a self-supervised… CONTINUE READING

View on ArXiv

Add to Library

Create Alert

Cite