update mindarmour roadmap

This commit is contained in:
yangyuan
2025-06-10 11:17:44 +08:00
parent 048a0ff7fc
commit 5fb7915b9b
4 changed files with 6 additions and 2 deletions

View File

@@ -27,7 +27,9 @@
## What is MindArmour
MindArmour focus on security and privacy of artificial intelligence. MindArmour can be used as a tool box for MindSpore users to enhance model security and trustworthiness and protect privacy data. MindArmour contains three module: Adversarial Robustness Module, Fuzz Testing Module, Privacy Protection and Evaluation Module.
MindArmour focus on security and privacy of artificial intelligence. It is committed to enhancing the trustworthiness of models and protecting the privacy of training and inference data. The current version (v2.0) mainly includes three modules: Adversarial Robustness Module, Fuzz Testing Module, Privacy Protection and Evaluation Module.
![mindarmour_roadmap](docs/roadmap_en.png)
### Adversarial Robustness Module

View File

@@ -27,7 +27,9 @@
## 简介
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。
MindArmour关注AI的安全和隐私问题。致力于增强模型的安全可信、保护训推数据隐私安全。当前版本v2.0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。
![mindarmour_roadmap](docs/roadmap.png)
### 对抗样本鲁棒性模块

BIN
docs/roadmap.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 122 KiB

BIN
docs/roadmap_en.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 136 KiB