A tool box for MindSpore users to enhance model security and trustworthiness.
MindArmour is designed for adversarial examples, including four submodule: adversarial examples generation, adversarial example detection, model defense and evaluation. The architecture is shown as follow：
This library uses MindSpore to accelerate graph computations performed by many machine learning models. Therefore, installing MindSpore is a pre-requisite. All other dependencies are included in setup.py.
- Download source code from Gitee.
git clone https://gitee.com/mindspore/mindarmour.git- Compile and install in MindArmour directory.
$ cd mindarmour
$ python setup.py install- Download whl package from MindSpore website, then run the following command:
pip install mindarmour-{version}-cp37-cp37m-linux_{arch}.whl
- Successfully installed, if there is no error message such as
No module named 'mindarmour'when execute the following command:
python -c 'import mindarmour'Guidance on installation, tutorials, API, see our User Documentation.
- MindSpore Slack - Ask questions and find answers.
Welcome contributions. See our Contributor Wiki for more details.
The release notes, see our RELEASE.