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.
 
 
 
 
i-robot 6fc4193ae8
!422 modify the error parameter types in 1.9
2 years ago
..
mindarmour.adv_robustness.attacks.rst modify doc 2 years ago
mindarmour.adv_robustness.defenses.rst modify the error parameter types in 1.9 2 years ago
mindarmour.adv_robustness.detectors.rst modify doc 2 years ago
mindarmour.adv_robustness.evaluations.rst modify doc 2 years ago
mindarmour.fuzz_testing.rst modify the format of API files 2 years ago
mindarmour.privacy.diff_privacy.rst !422 modify the error parameter types in 1.9 2 years ago
mindarmour.privacy.evaluation.rst !422 modify the error parameter types in 1.9 2 years ago
mindarmour.privacy.sup_privacy.rst modify links branch to r1.9 2 years ago
mindarmour.reliability.rst modify links branch to r1.9 2 years ago
mindarmour.rst !422 modify the error parameter types in 1.9 2 years ago
mindarmour.utils.rst modify doc 2 years ago

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