Ragarding the attacking mode in Class Attack.

[tao-bai]

Hi Harry, I see the below codes and feel a little confused.
When performing untargeted attacks, self._targeted = 1

cost = self._targeted*loss(outputs, labels)
grad = torch.autograd.grad(cost, images,retain_graph=False, create_graph=False)[0]
adv_images = images + self.eps*grad.sign()

Is it easier to understand to set self._targeted = -1 for untargeted attacks?
and modify corresponding lines

cost = self._targeted*loss(outputs, labels)
grad = torch.autograd.grad(cost, images,retain_graph=False, create_graph=False)[0]
adv_images = images - self.eps*grad.sign()

[Harry24k]

Thank you for your suggestion.
It seems to have been implemented in that way in order not to change much of the existing code when adding the targeted mode.
I think it would be better to change it.

[Harry24k]

Updated!

80e3741