1 Star 0 Fork 40

zheng-huanhuan / mindarmour

forked from MindSpore / mindarmour 
Create your Gitee Account
Explore and code with more than 5 million developers,Free private repositories !:)
Sign up
Clone or download
RELEASE.md 3.68 KB
Copy Edit Web IDE Raw Blame History
pkuliuliu authored 2020-08-20 17:21 . 0.7.0 release

Release 0.7.0-beta

Major Features and Improvements

Differential privacy model training

  • Privacy leakage evaluation.

    • Using Membership inference to evaluate the effectiveness of privacy-preserving techniques for AI.

Model robustness evaluation

  • Fuzzing based Adversarial Robustness testing.

    • Coverage-guided test set generation.

Bugfixes

Contributors

Thanks goes to these wonderful people:

Liu Liu, Xiulang Jin, Zhidan Liu, Luobin Liu and Huanhuan Zheng.

Contributions of any kind are welcome!

Release 0.6.0-beta

Major Features and Improvements

Differential privacy model training

  • Optimizers with differential privacy

    • Differential privacy model training now supports some new policies.

    • Adaptive Norm policy is supported.

    • Adaptive Noise policy with exponential decrease is supported.

  • Differential Privacy Training Monitor

    • A new monitor is supported using zCDP as its asymptotic budget estimator.

Bugfixes

Contributors

Thanks goes to these wonderful people:

Liu Liu, Huanhuan Zheng, XiuLang jin, Zhidan liu.

Contributions of any kind are welcome.

Release 0.5.0-beta

Major Features and Improvements

Differential privacy model training

  • Optimizers with differential privacy

    • Differential privacy model training now supports both Pynative mode and graph mode.

    • Graph mode is recommended for its performance.

Bugfixes

Contributors

Thanks goes to these wonderful people:

Liu Liu, Huanhuan Zheng, Xiulang Jin, Zhidan Liu.

Contributions of any kind are welcome!

Release 0.3.0-alpha

Major Features and Improvements

Differential Privacy Model Training

Differential Privacy is coming! By using Differential-Privacy-Optimizers, one can still train a model as usual, while the trained model preserved the privacy of training dataset, satisfying the definition of differential privacy with proper budget.

  • Optimizers with Differential Privacy(PR23, PR24)
    • Some common optimizers now have a differential privacy version (SGD/ Adam). We are adding more.
    • Automatically and adaptively add Gaussian Noise during training to achieve Differential Privacy.
    • Automatically stop training when Differential Privacy Budget exceeds.
  • Differential Privacy Monitor(PR22)
    • Calculate overall budget consumed during training, indicating the ultimate protect effect.

Bug fixes

Contributors

Thanks goes to these wonderful people: Liu Liu, Huanhuan Zheng, Zhidan Liu, Xiulang Jin Contributions of any kind are welcome!

Release 0.2.0-alpha

Major Features and Improvements

  • Add a white-box attack method: M-DI2-FGSM(PR14).
  • Add three neuron coverage metrics: KMNCov, NBCov, SNACov(PR12).
  • Add a coverage-guided fuzzing test framework for deep neural networks(PR13).
  • Update the MNIST Lenet5 examples.
  • Remove some duplicate code.

Bug fixes

Contributors

Thanks goes to these wonderful people: Liu Liu, Huanhuan Zheng, Zhidan Liu, Xiulang Jin Contributions of any kind are welcome!

Release 0.1.0-alpha

Initial release of MindArmour.

Major Features

  • Support adversarial attack and defense on the platform of MindSpore.
  • Include 13 white-box and 7 black-box attack methods.
  • Provide 5 detection algorithms to detect attacking in multiple way.
  • Provide adversarial training to enhance model security.
  • Provide 6 evaluation metrics for attack methods and 9 evaluation metrics for defense methods.

Comment ( 0 )

Sign in for post a comment

Python
1
https://git.oschina.net/Tinrry/mindarmour.git
git@git.oschina.net:Tinrry/mindarmour.git
Tinrry
mindarmour
mindarmour
master

Search