Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

By Hui-Po Wang, Ning Yu, Mario Fritz. 2020

31 citations recorded by the source corpus.

While Generative Adversarial Networks (GANs) show increasing performance and the level of realism is becoming indistinguishable from natural images, this also comes with high demands on data and computation. We show that state-of-the-art GAN models – such as they are being publicly released by researchers and industry – can be used for a range of applications beyond unconditional image generation. We achieve this by an iterative scheme that also allows gaining control over the image generation process despite the highly non-linear latent spaces of the latest GAN models. We demonstrate that this opens up the possibility to re-use state-of-the-art, difficult to train, pre-trained GANs with a high level of control even if only black-box access is granted. Our work also raises concerns and awareness that the use cases of a published GAN model may well reach beyond the creators’ intention, which needs to be taken into account before a full public release. Code is available at https://github.com/a514514772/hijackgan.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Mario Fritz
  4. Trevor Darrell
  5. Ming-Hsuan Yang
  6. Bernt Schiele
  7. Xiaogang Wang
  8. Li Fei-Fei

Citations in the corpus