MindArmour 1.9.1 Release Notes
Bug fixes
[BUGFIX] Fix a bug of HSJA method
Optimize Genetic attack method
Contributors
Thanks goes to these wonderful people:
Liu Liu and Xiulang Jin.
Contributions of any kind are welcome!
Thanks goes to these wonderful people:
Liu Zhidan, Zhang Shukun, Jin Xiulang, Liu Liu, Tang Cong, Yangyuan.
Contributions of any kind are welcome!
Thanks goes to these wonderful people:
Zhang Shukun, Liu Zhidan, Jin Xiulang, Liu Liu, Tang Cong, Yangyuan.
Contributions of any kind are welcome!
Thanks goes to these wonderful people:
Zhang Shukun, Liu Zhidan, Jin Xiulang, Liu Liu, Tang Cong, Yangyuan.
Contributions of any kind are welcome!
MindArmour 1.2.1 Release Notes
Bug fixes
[BUGFIX] Fix a bug of PGD method
[BUGFIX] Fix a bug of JSMA method
Contributors
Thanks goes to these wonderful people:
Liu Liu, Zhidan Liu, Luobin Liu and Xiulang Jin.
Contributions of any kind are welcome!
[BETA] Reconstruct AI Fuzz and Neuron Coverage Metrics
Thanks goes to these wonderful people:
Wu Xiaoyu,Liu Zhidan, Jin Xiulang, Liu Luobin, Liu Liu
Thanks goes to these wonderful people:
Wu Xiaoyu,Liu Zhidan, Jin Xiulang, Liu Luobin, Liu Liu
[Modify] ...
[Add] ...
[Delete] ...
[Add] ...
[BUGFIX] ...
Thanks goes to these wonderful people:
han.yin
[Modify] ...
[Add] ...
[Delete] ...
[Add] ...
[BUGFIX] ...
Thanks goes to these wonderful people:
han.yin
Thanks goes to these wonderful people:
Xiulang Jin, Zhidan Liu, Luobin Liu and Liu Liu.
Contributions of any kind are welcome!
Privacy leakage evaluation.
Fuzzing based Adversarial Robustness testing.
Thanks goes to these wonderful people:
Liu Liu, Xiulang Jin, Zhidan Liu and Luobin Liu.
Contributions of any kind are welcome!
Privacy leakage evaluation.
Fuzzing based Adversarial Robustness testing.
Thanks goes to these wonderful people:
Liu Liu, Xiulang Jin, Zhidan Liu, Luobin Liu and Huanhuan Zheng.
Contributions of any kind are welcome!
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
Thanks goes to these wonderful people:
Liu Liu, Huanhuan Zheng, XiuLang jin, Zhidan liu.
Contributions of any kind are welcome.
Optimizers with differential privacy
Differential privacy model training now supports both Pynative mode and graph mode.
Graph mode is recommended for its performance.
Thanks goes to these wonderful people:
Liu Liu, Huanhuan Zheng, Xiulang Jin, Zhidan Liu.
Contributions of any kind are welcome!
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.
Thanks goes to these wonderful people:
Liu Liu, Huanhuan Zheng, Zhidan Liu, Xiulang Jin
Contributions of any kind are welcome!
Thanks goes to these wonderful people:
Liu Liu, Huanhuan Zheng, Zhidan Liu, Xiulang Jin
Contributions of any kind are welcome!
Initial release of MindArmour.