This a TensorFlow Implementation of the Model Inversion Attack introduced with Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures (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.
conda env create --prefix="./.venv" -f environment.yml
conda activate "./.venv"
jupyter notebook Inversion.ipynb
The AT&T Face Dataset in this repository was downloaded from here (formerly available here).