diff --git a/README.md b/README.md
index 9f58382..f992fe7 100644
--- a/README.md
+++ b/README.md
@@ -12,17 +12,50 @@
 
 ## What is MindArmour
 
-A tool box for MindSpore users to enhance model security and trustworthiness and protect privacy data.
+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 model security module is designed for adversarial examples, including four submodule: adversarial examples generation, adversarial examples detection, model defense and evaluation. The architecture is shown as follow：
+### Adversarial Robustness Module
 
-![mindarmour_architecture](docs/mindarmour_architecture.png)
+Adversarial robustness module is designed for evaluating the robustness of the model against adversarial examples, 
+and provides model enhancement methods to enhance the model's ability to resist the adversarial attack and improve the model's robustness. 
+This module includes four submodule: Adversarial Examples Generation, Adversarial Examples Detection, Model Defense and Evaluation. 
 
-MindArmour differential privacy module Differential-Privacy implements the differential privacy optimizer. Currently, SGD, Momentum and Adam are supported. They are differential privacy optimizers based on the Gaussian mechanism. 
-This mechanism supports both non-adaptive and adaptive policy. Rényi differential privacy (RDP) and Zero-Concentrated differential privacy（ZDP） are provided to monitor differential privacy budgets. The architecture is shown as follow：
+The architecture is shown as follow：
+
+![mindarmour_architecture](docs/adversarial_robustness_en.png)
+
+### Fuzz Testing Module
+
+Fuzz Testing module is a security test for AI models. We introduce neuron coverage gain as a guide to fuzz testing according to the characteristics of neural networks. 
+Fuzz testing is guided to generate samples in the direction of increasing neuron coverage rate, so that the input can activate more neurons and neuron values have a wider distribution range to fully test neural networks and explore different types of model output results and wrong behaviors.
+
+The architecture is shown as follow：
+
+![fuzzer_architecture](docs/fuzzer_architecture_en.png)
+
+### Privacy Protection and Evaluation Module
+
+Privacy Protection and Evaluation Module includes two modules: Differential Privacy Training Module and Privacy Leakage Evaluation Module.
+
+#### Differential Privacy Training Module
+
+Differential Privacy Training Module implements the differential privacy optimizer. Currently, SGD, Momentum and Adam are supported. They are differential privacy optimizers based on the Gaussian mechanism. 
+This mechanism supports both non-adaptive and adaptive policy. Rényi differential privacy (RDP) and Zero-Concentrated differential privacy（ZCDP） are provided to monitor differential privacy budgets. 
+
+The architecture is shown as follow：
 
 ![dp_architecture](docs/differential_privacy_architecture_en.png)
 
+#### Privacy Leakage Evaluation Module
+
+Privacy Leakage Evaluation Module is used to assess the risk of a model revealing user privacy. The privacy data security of the deep learning model is evaluated by using membership inference method to infer whether the sample belongs to training dataset.
+
+The architecture is shown as follow：
+
+![privacy_leakage](docs/privacy_leakage_en.png)
+
+
 ## Setting up MindArmour
 
 ### Dependencies
diff --git a/README_CN.md b/README_CN.md
index c526a4b..aae9618 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -12,16 +12,42 @@
 
 ## 简介
 
-MindArmour可用于增强模型的安全可信、保护用户的数据隐私。
+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。
 
-模型安全主要针对对抗样本，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。对抗样本的架构图如下：
+### 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。
 
-![mindarmour_architecture](docs/mindarmour_architecture_cn.png)
+对抗样本鲁棒性模块的架构图如下：
 
-隐私保护支持差分隐私，包括动态或者非动态的差分隐私SGD、Momentum、Adam优化器，噪声机制支持高斯分布噪声、拉普拉斯分布噪声，差分隐私预算监测包含ZDP、RDP。差分隐私的架构图如下：
+![mindarmour_architecture](docs/adversarial_robustness_cn.png)
+
+### Fuzz Testing模块
+Fuzz Testing模块是针对AI模型的安全测试，根据神经网络的特点，引入神经元覆盖率，作为Fuzz测试的指导，引导Fuzzer朝着神经元覆盖率增加的方向生成样本，让输入能够激活更多的神经元，神经元值的分布范围更广，以充分测试神经网络，探索不同类型的模型输出结果和错误行为。
+
+Fuzz Testing模块的架构图如下：
+
+![fuzzer_architecture](docs/fuzzer_architecture_cn.png)
+
+### 隐私保护模块
+
+隐私保护模块包含差分隐私训练与隐私泄露评估。
+
+#### 差分隐私训练模块
+
+差分隐私训练包括动态或者非动态的差分隐私SGD、Momentum、Adam优化器，噪声机制支持高斯分布噪声、拉普拉斯分布噪声，差分隐私预算监测包含ZCDP、RDP。
+
+差分隐私的架构图如下：
 
 ![dp_architecture](docs/differential_privacy_architecture_cn.png)
 
+#### 隐私泄露评估模块
+
+隐私泄露评估模块用于评估模型泄露用户隐私的风险。利用成员推理方法来推测样本是否属于用户训练数据集，从而评估深度学习模型的隐私数据安全。
+
+隐私泄露评估模块框架图如下：
+
+![privacy_leakage](docs/privacy_leakage_cn.png)
+
 
 ## 开始
 
diff --git a/docs/adversarial_robustness_cn.png b/docs/adversarial_robustness_cn.png
new file mode 100644
index 0000000..e47ed78
Binary files /dev/null and b/docs/adversarial_robustness_cn.png differ
diff --git a/docs/adversarial_robustness_en.png b/docs/adversarial_robustness_en.png
new file mode 100644
index 0000000..5caa0e2
Binary files /dev/null and b/docs/adversarial_robustness_en.png differ
diff --git a/docs/differential_privacy_architecture_cn.png b/docs/differential_privacy_architecture_cn.png
index 8a423a2..ef8bda1 100644
Binary files a/docs/differential_privacy_architecture_cn.png and b/docs/differential_privacy_architecture_cn.png differ
diff --git a/docs/differential_privacy_architecture_en.png b/docs/differential_privacy_architecture_en.png
index 0240d22..f3da383 100644
Binary files a/docs/differential_privacy_architecture_en.png and b/docs/differential_privacy_architecture_en.png differ
diff --git a/docs/fuzzer_architecture_cn.png b/docs/fuzzer_architecture_cn.png
new file mode 100644
index 0000000..d714866
Binary files /dev/null and b/docs/fuzzer_architecture_cn.png differ
diff --git a/docs/fuzzer_architecture_en.png b/docs/fuzzer_architecture_en.png
new file mode 100644
index 0000000..1f4c413
Binary files /dev/null and b/docs/fuzzer_architecture_en.png differ
diff --git a/docs/mindarmour_architecture.png b/docs/mindarmour_architecture.png
deleted file mode 100644
index 5cbcf9b..0000000
Binary files a/docs/mindarmour_architecture.png and /dev/null differ
diff --git a/docs/mindarmour_architecture_cn.png b/docs/mindarmour_architecture_cn.png
deleted file mode 100644
index 9edccab..0000000
Binary files a/docs/mindarmour_architecture_cn.png and /dev/null differ
diff --git a/docs/privacy_leakage_cn.png b/docs/privacy_leakage_cn.png
new file mode 100644
index 0000000..99f4e4c
Binary files /dev/null and b/docs/privacy_leakage_cn.png differ
diff --git a/docs/privacy_leakage_en.png b/docs/privacy_leakage_en.png
new file mode 100644
index 0000000..1092978
Binary files /dev/null and b/docs/privacy_leakage_en.png differ