Timezone: »

 
Poster
Adversarial Self-Defense for Cycle-Consistent GANs
Dina Bashkirova · Ben Usman · Kate Saenko

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #120
in Deep Learning -- Generative Models »

The goal of unsupervised image-to-image translation is to map images from one domain to another without the ground truth correspondence between the two domains. State-of-art methods learn the correspondence using large numbers of unpaired examples from both domains and are based on generative adversarial networks. In order to preserve the semantics of the input image, the adversarial objective is usually combined with a cycle-consistency loss that penalizes incorrect reconstruction of the input image from the translated one. However, if the target mapping is many-to-one, e.g. aerial photos to maps, such a restriction forces the generator to hide information in low-amplitude structured noise that is undetectable by human eye or by the discriminator. In this paper, we show how such self-attacking behavior of unsupervised translation methods affects their performance and provide two defense techniques. We perform a quantitative evaluation of the proposed techniques and show that making the translation model more robust to the self-adversarial attack increases its generation quality and reconstruction reliability and makes the model less sensitive to low-amplitude perturbations. Our project page can be found at ai.bu.edu/selfadv.

Keywords: Deep Learning -> Generative Models · Algorithms -> Unsupervised Learning; Applications -> Computer Vision; Deep Learning -> Adversarial Networks

Author Information

Dina Bashkirova (Boston University)
Ben Usman (Boston University)
Kate Saenko (Boston University)

More from the Same Authors