We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 66a64a6 commit 96d0d76Copy full SHA for 96d0d76
art/attacks/evasion/projected_gradient_descent/projected_gradient_descent_tensorflow_v2.py
@@ -239,9 +239,6 @@ def _generate_batch(
239
perturbed.
240
:param eps: Maximum perturbation that the attacker can introduce.
241
:param eps_step: Attack step size (input variation) at each iteration.
242
- :param mask: An array with a mask broadcastable to input `x` defining where to apply adversarial perturbations.
243
- Shape needs to be broadcastable to the shape of x and can also be of the same shape as `x`. Any
244
- features for which the mask is zero will not be adversarially perturbed.
245
:return: Adversarial examples.
246
"""
247
adv_x = x
0 commit comments