-
Hello! I ran your code to train a model by PGD on WideResNet, which you provide, but the accuracy is far less than your provided pre-trained model, and the training is too slow and time-consuming, cou…
-
I am not able to create an attack instance when I am using loaded saved model (.pth file) for generating adversarial samples, can you please help find out, what can be the potential issue in this.
…
-
Sorry for bothering, when I run FF/FGS and FF/BIM for test accuracy, I got the values different from the paper. (FF/FGS: 6.13% and FF/BIM: 12.20%)
ps. I use the command below
python cifar_keras.p…
-
I tried FGSM attack on MNIST clean dataset, and I got 49% accuracy,
which is too large compared to 6.4% [Madry, https://arxiv.org/pdf/1706.06083.pdf]
Am i missing something?
I'd like to ask i…
-
I notice that your code only have un-target attack part. But target-attack, where we can specify the target class mannually is loss/missing?
-
Dear researchers, I am really impressed by your work on it. I have a few questions that I hope you could help clarify for me. I find the data for an architecture is organized like this:
```python
…
-
Some attacks implemented in torchattacks have better results when used in combinations with other attacks, as reported in their papers.
For example, [the paper proposing DI2-FGSM](https://arxiv.or…
-
-
Hello, I hope you're well. I went through your paper and supplementary material to understand how a strategy network generates attack types. My understanding through code and architectural diagram is …
-
It seems like FGSM and PGD assume a hypercube input (from the uniform radius parameter ϵ). These algorithms both seem like they could support a hyper-rectangle input with small modifications. I was wo…