They don't claim the articles are fake, but the way they evaluate their defenses is not the most relevant. They show that, even though being robust to standard attacks, it is still possible for a GAN to fool the proposed defenses (e.g. https://arxiv.org/pdf/1804.03286.pdf …)
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.