https://github.com/yashkant/model-inversion-attack
Implementation of the Model Inversion Attack introduced with Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures (Fredrikson Et al.)
https://github.com/yashkant/model-inversion-attack
model-inversion-attacks tensorflow
Last synced: 6 months ago
JSON representation
Implementation of the Model Inversion Attack introduced with Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures (Fredrikson Et al.)
- Host: GitHub
- URL: https://github.com/yashkant/model-inversion-attack
- Owner: yashkant
- Created: 2018-04-08T04:52:07.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2023-02-26T22:48:38.000Z (over 2 years ago)
- Last Synced: 2025-04-02T15:04:10.034Z (6 months ago)
- Topics: model-inversion-attacks, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 180 KB
- Stars: 83
- Watchers: 4
- Forks: 21
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Model-Inversion-Attack
This a TensorFlow Implementation of the Model Inversion Attack introduced with [Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures](https://dl.acm.org/citation.cfm?id=2813677) (Fredrikson Et al.)
The gradient step and the final output of the attack loop is pre-processed with ZCA whitening and Global Contrast Normalization with Pylearn2, this helps to preserve the facial features present in the input dataset.
The important dependencies of this project include:
- TensorFlow
- Pylearn2
- Matplotlib
In case you run into some trouble installing the dependencies take a look at this [issue](https://github.com/yashkant/Model-Inversion-Attack/issues/1).
# Directions to Use
1. Download the AT&T Face Dataset from [here](https://www.kaggle.com/kasikrit/att-database-of-faces?select=s1)
2. Extract the dataset and replace the path variable in the 3rd cell of the inversion notebook.