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.
 
 
 
 
君君臣臣君 d9165dcefc
update examples/face_adversarial_attack/example/AFR.py.
3 years ago
..
opencv_photo update 3 years ago
AFR.py update examples/face_adversarial_attack/example/AFR.py. 3 years ago
README.md update 3 years ago
camera.py update 3 years ago
example_non-target_attack.py update 3 years ago
example_target_attack.py update 3 years ago
loss_design.py update 3 years ago
test.py update 3 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