search

bethgelab / foolbox

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
https://foolbox.jonasrauber.de
MIT License
2.73k stars 425 forks source link

Logit optimization #696

Open md-bayazid opened 2 years ago

md-bayazid commented 2 years ago

I got stuck at understanding about when the logit is coming and where to pass it for optimization. Is the logit calculated after the change of variables? How can I understand the execution sequence of the following link?

https://github.com/bethgelab/foolbox/blob/master/foolbox/attacks/carlini_wagner.py