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.

README.md 2.1 kB

5 years ago
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374
  1. # MindArmour
  2. - [What is MindArmour](#what-is-mindarmour)
  3. - [Setting up](#setting-up-mindarmour)
  4. - [Docs](#docs)
  5. - [Community](#community)
  6. - [Contributing](#contributing)
  7. - [Release Notes](#release-notes)
  8. - [License](#license)
  9. ## What is MindArmour
  10. A tool box for MindSpore users to enhance model security and trustworthiness.
  11. 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:
  12. ![mindarmour_architecture](docs/mindarmour_architecture.png)
  13. ## Setting up MindArmour
  14. ### Dependencies
  15. 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`.
  16. ### Installation
  17. #### Installation for development
  18. 1. Download source code from Gitee.
  19. ```bash
  20. git clone https://gitee.com/mindspore/mindarmour.git
  21. ```
  22. 2. Compile and install in MindArmour directory.
  23. ```bash
  24. $ cd mindarmour
  25. $ python setup.py install
  26. ```
  27. #### `Pip` installation
  28. 1. Download whl package from [MindSpore website](https://www.mindspore.cn/versions/en), then run the following command:
  29. ```
  30. pip install mindarmour-{version}-cp37-cp37m-linux_{arch}.whl
  31. ```
  32. 2. Successfully installed, if there is no error message such as `No module named 'mindarmour'` when execute the following command:
  33. ```bash
  34. python -c 'import mindarmour'
  35. ```
  36. ## Docs
  37. Guidance on installation, tutorials, API, see our [User Documentation](https://gitee.com/mindspore/docs).
  38. ## Community
  39. - [MindSpore Slack](https://join.slack.com/t/mindspore/shared_invite/enQtOTcwMTIxMDI3NjM0LTNkMWM2MzI5NjIyZWU5ZWQ5M2EwMTQ5MWNiYzMxOGM4OWFhZjI4M2E5OGI2YTg3ODU1ODE2Njg1MThiNWI3YmQ) - Ask questions and find answers.
  40. ## Contributing
  41. Welcome contributions. See our [Contributor Wiki](https://gitee.com/mindspore/mindspore/blob/master/CONTRIBUTING.md) for more details.
  42. ## Release Notes
  43. The release notes, see our [RELEASE](RELEASE.md).
  44. ## License
  45. [Apache License 2.0](LICENSE)

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。