hummingbird
/
mindarmour
Not watched
2
0
Fork 0
Code
Releases 17 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
71 Commits
18 Branches
193 MB
132 Download
 
 
 
 
Branch: r0.5
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'r0.5'
${ noResults }
mindspore-ci-bot 456a8a03a9 !47 update release 5 years ago
.gitee Add issue and PR templates for gitee and github 5 years ago
.github Add issue and PR templates for gitee and github 5 years ago
docs initial version 5 years ago
example update default value 5 years ago
mindarmour !45 fix issue 5 years ago
tests change DPModel param l2_norm_clip to norm_clip. 5 years ago
.gitignore initial version 5 years ago
LICENSE initial version 5 years ago
NOTICE initial version 5 years ago
README.md initial version 5 years ago
RELEASE.md update release. 5 years ago
package.sh update package.sh configuration. 5 years ago
requirements.txt 1. Add DI2-FGSM method in iterative_gradient_method.py 5 years ago
setup.py Add differential privacy in GRAPH MODE context mode. 5 years ago

README.md

MindArmour

What is MindArmour

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：

mindarmour_architecture

Setting up MindArmour

Dependencies

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.

Installation

Installation for development

  1. Download source code from Gitee.
git clone https://gitee.com/mindspore/mindarmour.git
  1. Compile and install in MindArmour directory.
$ cd mindarmour
$ python setup.py install

Pip installation

  1. Download whl package from MindSpore website, then run the following command:
pip install mindarmour-{version}-cp37-cp37m-linux_{arch}.whl
  1. Successfully installed, if there is no error message such as No module named 'mindarmour' when execute the following command:
python -c 'import mindarmour'

Docs

Guidance on installation, tutorials, API, see our User Documentation.

Community

Contributing

Welcome contributions. See our Contributor Wiki for more details.

Release Notes

The release notes, see our RELEASE.

License

Apache License 2.0

Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

MindArmour关注AI的安全和隐私问题。致力于增强模型的安全可信、保护用户的数据隐私。主要包含3个模块：对抗样本鲁棒性模块、Fuzz Testing模块、隐私保护与评估模块。 对抗样本鲁棒性模块 对抗样本鲁棒性模块用于评估模型对于对抗样本的鲁棒性，并提供模型增强方法用于增强模型抗对抗样本攻击的能力，提升模型鲁棒性。对抗样本鲁棒性模块包含了4个子模块：对抗样本的生成、对抗样本的检测、模型防御、攻防评估。

Python Markdown Text other