hummingbird
/
mindarmour
Not watched
2
0
Fork 0
Code
Releases 17 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
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.
44 Commits
18 Branches
193 MB
5 Download
 
 
 
 
Tree: ec9d46a7e1
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'ec9d46a7e1'
${ noResults }
mindarmour/tests/ut/python
ZhidanLiu ec9d46a7e1 fix parameter check 5 years ago
..
attacks fix parameter check 5 years ago
defenses modify input batch_size for defenses tests 5 years ago
detectors fix parameter check 5 years ago
diff_privacy [CT][MA][DP]param of DPModel:norm_clip,use default, runtime error][DP]param of DPModel:norm_clip=0, runtime error][diff_privacy][Pref] use DPModel ，the performance of lenet deteriorates too much 5 years ago
evaluations fix pylint warning. 5 years ago
fuzzing fix pylint warning. 5 years ago
test_data initial version 5 years ago
utils fix pylint warning. 5 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

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