fast_adversarial

fast_adversarial copied to clipboard

Hi! I am having a hard time reproducing the results (on MNIST, for example) and I have found that they differ when I change the pytorch version. I observe the...

latorrefabian

Hi, Does anyone can help me to understand why not using clean samples during training? Will it reduce the performance? Thanks~

coordxyz

Bumps [numpy](https://github.com/numpy/numpy) from 1.17.2 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

Hello, Thanks for your valuable work. I would like to understand the methodology behind the division of epsilon and alpha values with standard deviation. ``` epsilon = (args.epsilon / 255.)...

DuyguSerbes

In the implemenation of fgsm for mnist, you do not clamp the initatial perturbation - meaning you calculate gradient based on out of bounds data points: # delta = torch.zeros_like(X).uniform_(-args.epsilon,...

max-kaufmann

Hello Leslie Rice and Eric Wong, Congratulations on your significant work！！ I found the model is always set to `training` mode during adversarial training period. However, I think when we...

vtddggg

Reproduce the result of CIFAR-10 from the default setting

1

Hi, I'm running the repo with the default configuration for CIFAR-10, however, here is the reported Accuracy I got from the trained model after 15 epochs: ``` Total train time:...

baogiadoan

hi, during the training with my custom objective loss, I realized that sometimes the model went wrong and produce "nan" and become invalid; which I didn't face before with other...

baogiadoan

Why do we need to do clamp(delta, lower_limit - X, upper_limit - X)？

2

hyserendipity

Hi, I tried to use this method on CIFAR-100 with the same parameter settings as CIFAR-10. But the results are terrible that the test adversarial accuracies are less than 2%....

LiuJia68