-
-
Hi i want a clarification, to use the attacks inside of the library I should give as input the same input as the paper? Or for example i can give audio inputs to the Deepfool attack?
-
Hi! Nice to see such an interesting paper with code released.
I have a question about your Pytorch code.
In line 100 (x = x + alpha_beta * torch.sign(noise) + projection) of the script "project_…
-
### General information
- Library version(s): lab-test branch, latest commit
## Bug report
#### Background
We currently develop a staking pool implementation for albatross. We use the devnet…
-
I'm trying to implement an FGSM attack on TRPO but I don't know how should I use zero_grad with the TRPO model
here is a part of the code
```python
loss2 = F.nll_loss(model.action_probability(st…
-
I am using PyTorch CIFAR-10 dataset, with the following transformations:
transform_train = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.20…
-
**Description**
When running eval_model.py on adversarial examples not already included but rather generated by craft_adversarial_examples.py, there is an IndexError in metrics.py. This error does no…
-
i am working on tensorflow/slim package there are training file and evaluation file , i have done the training successfully but when i run evaluation file get error .
the error from issue in termin…
-
Hi,
Could you please provide CIFAR10_PCL_AdvTrain_PGD.pth.tar and CIFAR10_PCL_AdvTrain_FGSM.pth.tar?
And could you clarify what is robust_model.pth.tar for?
-
Hi, I'm running Foolbox `3.0.0b1` with PyTorch `1.2.0` on MNIST using the below code snippet. For some reason it seems that CWL2 performs very poorly compared to FGSM. My model still is able to classi…