-
***The issue tracker should only be used to report bugs or feature requests. If you are looking for support from other library users, please ask a question on [StackOverflow](https://stackoverflow.com…
-
https://github.com/tensorflow/cleverhans has BACKPROP_THROUGH_ATTACK attribute is exactly what your idea in your paper
-
https://github.com/bethgelab/foolbox/blob/c3dd8020f7bf289bc9c778eb3f8586188ee3609e/foolbox/attacks/gradient.py#L40
I am not certain if this `i < 20` makes sense? I understand that after one iterati…
-
the parameter of attack is like MomentumIterativeAttack(model,F.nll_loss),could i pass a list of model to this???
-
Hello!
I learn how to use advertorch from this site, https://github.com/BorealisAI/advertorch/blob/master/advertorch_examples/tutorial_attack_defense_bpda_mnist.ipynb.
I wonder how to know if the c…
-
**Describe the bug**
For keras model, if I load the pretrained weights ahead of adv generate function, there is Error with "uninitialized weight".
So I have to load weights after that, I donot …
-
**Describe the bug**
I am unable to create any instances of `art.classifiers.KerasClassifier` whenever the underlying Keras model contains an Embedding layer. Using the TensorFlow backend, this invar…
-
**Describe the bug**
Modified example produces strange output. Please see code and images below.
**To Reproduce**
Steps to reproduce the behavior:
1. Run the code below
2. Save produced adversa…
-
This might require making some changes to the library to support this new mode.
-
**Describe the bug**
For new data normal evaluation(non adversarial data) is working fine, but for adversarial examples (being generated out of new data) , error is getting thrown when evaluation is …