Published September 26, 2020
| Version v3.2.1
Software
Open
Foolbox Native: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX
- 1. University of Tübingen
Description
Foolbox is a Python library that lets 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, and JAX.
Files
bethgelab/foolbox-v3.2.1.zip
Files
(9.0 MB)
Name | Size | Download all |
---|---|---|
md5:b104e0274abe629645b6d9d98a42c9f8
|
9.0 MB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/bethgelab/foolbox/tree/v3.2.1 (URL)