ZhouZhenkun / Model-Attacking-Defending

In this project, I implemented FGSM and the basic iterative method to attack a pre-trained model. Then I tried to protect my model by doing randomization to the images before I feed them into my model.

Model Attacking & Defending

A project that includes adversarial attacks and passive defenses of a model

Task

Conduct the Fast Gradient Sign Method and the basic iterative method to attack a pre-trained model.
Then, protect the model by conducting randomization to the images before feeding them into the model.

Run on Colab (cannot save your own version)

• Access the notebook to run the codes: https://colab.research.google.com/drive/1WEMfMOh0r6lC8aLnux3E6UZw1tzFgTAe?usp=sharing

Run on Colab (can save your own version)

• Run this command: git clone https://github.com/b05702057/Model-Attacking-Defending.git
• Upload the .ipynb files to your google drive and open it with colab