This Repository contains the PyTorch Implementation for the ICLR'18 paper 《Spatially Transformed Adversarial Examples》
The DFFD dataset is comprised of multiple publically available datasets and images that are synthesized/manipulated using publically available methods. By incorporating multiple sources for real images, we are able to include varying resolution and image quality for both real and synthetic/manipulated images.
XnceptionNet(99.7 acc), MesoNet(95.3 acc), MesoInceptionNet(93.2 acc)
FGSM, PGD, stAdv
An example of stAdv generated adversarial example
