Skip to content
master
Switch branches/tags
Code

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
Oct 26, 2020
Jun 30, 2020

An Imperceptible Anti-forensic Method, Models and Dataset

Perception matters: exploring imperceptible and transferable anti-forensics forGAN-generated fake face imagery detection

This repository contains the code, models and dataset for the project "Perception matters: exploring imperceptible and transferable anti-forensics for GAN-generated fake face imagery detection".

Implementation

This code has been tested on Ubuntu 16.04 system, with following pre-requisites.

Pre-requisites

  1. python >=3.6.10
  2. PyTorch >=0.4.1
  3. torchvision >=0.2.1
  4. Pillow >=5.4.1

Dataset

The face dataset we used is an image subset dataset downloaded from here.

If you agree with the license in here, you might be permitted to download the downsampled image subset from here.

This face image subset consists of 40,000 real face images and 40,000 fake face images with image resolution as 128x128. For real or fake face images, the dataset splits are: 30,000 images are used for model training; 5,000 images for validation; and the rest 5,000 for test.

After downloading the dataset, please unzip and put them in the data directory.

Models

The pretrained deep learning-based fake face forensic models can be downloaded here. After downloading pretrained models, please uncompress and put them in the checkPoint directory.

Run attacks

cd attacks
bash ./run_attack.sh

If you find our code useful in your research, please consider citing our work:

About

An imperceptible and transferable anti-forensic method for fake face imagery detection.

Resources

Releases

No releases published

Packages

No packages published