A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
MIT License
Bot releases are hidden (Show)
Published by jonasrauber almost 7 years ago
BoundaryAttack less verbose
Published by jonasrauber almost 7 years ago
BoundaryAttack added: a new, powerful decision-based attack that does not rely on gradients or probabilities
Published by jonasrauber about 7 years ago
Performance improvements and minor changes. Easier to write fast attacks.
Published by jonasrauber about 7 years ago
several bugfixes
Published by jonasrauber about 7 years ago
Fixes a bug in ContrastAttack
when the lower bound is non-zero (thanks to @whg1g15)
Published by jonasrauber about 7 years ago
MXNet model bugfixes
improved support for other Keras backends (in particular Theano; in addition to TensorFlow)
Published by jonasrauber about 7 years ago
Keras model improvements
Published by jonasrauber about 7 years ago
MXNet model improvements
Published by jonasrauber about 7 years ago
Preprocessing has been changed and fixed.
Published by jonasrauber over 7 years ago
fix for the Readme on PyPI
Published by jonasrauber over 7 years ago
Our technical report is now available on arXiv: https://arxiv.org/abs/1707.04131
Published by jonasrauber over 7 years ago
Published by jonasrauber over 7 years ago
added support for a preprocessing callback to the PyTorch model
Published by jonasrauber over 7 years ago
Bugfix for the PyTorch interface when using GPUs, contributed by @ducha-aiki.
Published by jonasrauber over 7 years ago
Support for older versions of setuptools
.
Published by jonasrauber over 7 years ago
Published by jonasrauber over 7 years ago
added support for Python 2.7
Published by jonasrauber over 7 years ago
Published by jonasrauber over 7 years ago