Python toolbox to create adversarial examples that fool neural networks
Project description
AdvBox是一款由百度安全实验室研发,在百度大范围使用的AI模型安全工具箱,目前原生支持PaddlePaddle、PyTorch、Caffe2、MxNet、Keras以及TensorFlow平台,方便广大开发者和安全工程师可以使用自己熟悉的框架。 AdvBox同时支持GraphPipe,屏蔽了底层使用的深度学习平台,用户可以通过几个命令就可以对PaddlePaddle、PyTorch、Caffe2、MxNet、CNTK、ScikitLearn以及TensorFlow平台生成的模型文件进行黑盒攻击。
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
advbox-0.4.1-py2-none-any.whl
(130.5 kB
view hashes)