Shen et al. introduce APE-GAN, a generative adversarial network (GAN) trained to remove adversarial noise from adversarial examples. In specific, as illustrated in Figure 1, a GAN is traiend to specifically distinguish clean/real images from adversarial images. The generator is conditioned on th einput image and can be seen as auto encoder. Then, during testing, the generator is applied to remove the adversarial noise.
Figure 1: The proposed adversarial perturbation eliminating GAN (APE-GAN), see the paper for details.
Shen et al. introduce APE-GAN, a generative adversarial network (GAN) trained to remove adversarial noise from adversarial examples. In specific, as illustrated in Figure 1, a GAN is traiend to specifically distinguish clean/real images from adversarial images. The generator is conditioned on th einput image and can be seen as auto encoder. Then, during testing, the generator is applied to remove the adversarial noise.
Figure 1: The proposed adversarial perturbation eliminating GAN (APE-GAN), see the paper for details.