-
I find when I set the params as 'max_iter=64, max_eval=10000, init_eval=100' to attack a ResNet on MNIST, it is very time-consuming. I use a batch including 200 MNIST images but the algorithm spends m…
-
I am facing a problem while computing predictions for adversaries after saving them to disk. I am using a **VGG16 model in PyTorch**. When foolbox generates an adversary and I try to get prediction de…
-
Hello,
I've run into a similiar issue as #194 while trying to run example code. I am recieving a following error while creating the attack ( adversarial = attack(image, label) )
RuntimeError: Expe…
-
```
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
in
1 attack = foolbox.attacks.FG…
-
I am trying to implement gradient based attacks such as fgsm ,Bim,Jsma using foolbox. I took a look at the example in the documentation and accordingly implemented the attack on my own model. My model…
-
I'm not sure why this happens, but this throws an error only if the formula.tools package is loaded. I'm guessing it must be a bug in formula.tools:
```
library(formula.tools)
library(lmerTest)
m1
-
Hello,
I suspect I may have encountered a bug in the implementation of the Carlini-Wagner L2 attack. Consider the following code:
```
import numpy as np
import keras
import foolbox
from kera…
-
Hi.
I am using ResNet50 with keras based on the example code. FGSM works fine but LBFGS is unusually slow. Even after setting maxiter = 5, it takes more than a minute to produce the adversarial exa…
-
I'm trying to plot a histogram and its fitted function on the same pad, with the different components of the model drawn separately in different colours. Somehow the Draw("SAME") causes the plot to "f…
-
I'm using `fit_generator` passing it separate generators for the training and validation sets, defined as follows:
```
# create generator following logic in
# https://stackoverflow.com/questions…