Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images
Reverse_Engineering_GMs
Official Pytorch implementation of paper “Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images”.
The paper and supplementary can be found at https://arxiv.org/abs/2106.07873
Prerequisites
- PyTorch 1.5.0
- Numpy 1.14.2
- Scikit-learn 0.22.2
Getting Started
Datasets
For reverse enginnering:
For deepfake detection:
- Download the CelebA/LSUN dataset
For image_attribution:
- Generate 110,000 images for four different GAN models as specified in https://github.com/ningyu1991/GANFingerprints/
- For real images, use 110,000 of CelebA dataset.
- For training: we used 100,000 images and remaining 10,000 for testing.
Training
- Provide the train and test path in respective codes as sepecified below.
- Provide the model path to resume training
- Run the code
For reverse engineering, run:
python reverse_eng.py
For deepfake detection, run:
python deepfake_detection.py
For image attribution, run: