CleverHans is a Python library to benchmark machine learning systems' vulnerability to adversarial examples.
CleverHans is built on top of tensorflow.
Questions tagged [cleverhans]
49 questions
0
votes
1 answer
Memory Consumption of Jacobian Dataset Augmentation
I am trying to replicate results from https://arxiv.org/abs/1602.02697,
but using images size 224x224x3 following the black-box tutorial https://github.com/tensorflow/cleverhans/blob/master/cleverhans_tutorials/mnist_blackbox.py
However, I am…
Martin Matak
- 351
- 1
- 3
- 8
0
votes
1 answer
which attack in cleverhans is grey box attack and which is white/black box attack in cleverhans library?
I use https://github.com/tensorflow/cleverhans to generate adversarial images, but the categories of attack algoritm is not provided.
All the attack algorithm codes are listed here:…
machen
- 283
- 2
- 10
-1
votes
1 answer
ModuleNotFoundError: No module named 'cleverhans.utils_keras' in Colab
I used the following to install cleverhans in Colab:
!pip install -qq -e git+http://github.com/tensorflow/cleverhans.git#egg=cleverhans
import sys
sys.path.append('/content/src/cleverhans')
import cleverhans
And it seems to work good. Then I use…
Avi
- 2,247
- 4
- 30
- 52
-1
votes
1 answer
Why cleverhans pytorch tutorial using log_softmax instead of logits as output
When generating adversarial examples, it is typically using logits as the output of the neural network, and then train the network with cross-entropy.
However, I found that the tutorial of cleverhans uses log softmax and then convert the pytorch…
Denny Law
- 3
- 2