foolbox
Foolbox Native is an adversarial attacks library that works natively with PyTorch, TensorFlow and JAX
Foolbox Native is an adversarial attacks library that works natively with PyTorch, TensorFlow and JAX
To install this package, run one of the following:
Foolbox is a Python library that let's you easily run adversarial attacks against machine learning models like deep neural networks. It is built on top of EagerPy and works natively with models in PyTorch, TensorFlow, JAX, and NumPy.
Summary
Foolbox Native is an adversarial attacks library that works natively with PyTorch, TensorFlow and JAX
Last Updated
Feb 23, 2021 at 15:15
License
MIT
Total Downloads
20.2K
Supported Platforms
GitHub Repository
https://github.com/bethgelab/foolbox/Documentation
https://foolbox.readthedocs.io/en/stable/