Anshuman Suri
Anshuman Suri
I trained a model using the dev branch (tensorflow v1.12) and tried running that model in the demo branch, but got the above error in the run-demo.py file.
The original work by Madry et al mentions that in the optimization loop of their attack, they normalize the gradient before multiplying it with the step size. I may have...
Having read about [Houdini ](http://papers.nips.cc/paper/7273-houdini-fooling-deep-structured-visual-and-speech-recognition-models-with-adversarial-examples.pdf)and its success in various domains to construct adversarial samples, it would be great to have it in cleverhans.
These errors show up (after making a few changes for TF version compatibility). The code-base seems to be heavily outdated. 
Different tld options now taken as input. Needs testing (not been able to do so,as the API key associated with the current account is invalid and a new one is...
It seems the data pre-processing does not convert the graphs to simple graphs. Even though they are undirected and unweighted, some nodes in the graphs have multiple parallel edges. This...
Add link to blog on one-shot learning in Keras
When using the _theano_ backend for running this code, the fine-tuning of the top layer runs perfectly fine. However, as soon as the tweaking of the penultimate layer starts, the...
Hey, Greate codebase- well-written and nicely documented! I spent the last few days looking for good and efficient ways to compute the Hessian of a model in Pytorch but almost...