A Sanity Check for AI-generated Image Detection

Official implementation of 'A Sanity Check for AI-generated Image Detection'.

Introduction

We conduct a sanity check on "whether the task of AI-generated image detection has been solved". To start with, we present Chameleon dataset, consisting AI-generated images that are genuinely challenging for human perception. To quantify the generalization of existing methods, we evaluate 9 off-the-shelf AI-generated image detectors on Chameleon dataset. Upon analysis, almost all models classify AI-generated images as real ones. Later, we propose AIDE~(AI-generated Image DEtector with Hybrid Features), which leverages multiple experts to simultaneously extract visual artifacts and noise patterns.

News

TODO: Release the Chamelon dataset.
🔥🔥🔥We release the code and checkpoints of AIDE.

Requirements

We test the codes in the following environments, other versions may also be compatible:

CUDA 11.3
Python 3.10
Pytorch 1.11.0

Installation

Please refer to install.md for installation.

Get Started

Please see Training.md for details.

Dataset

Training Set

We adopt the training set in CNNSpot and GenImage.

Test Set

The whole test set we used in our experiments can be downloaded from AIGCDetectBenchmark and GenImage.

Model Zoo

Our training checkpoints can be downloaded from link.

Acknowledgement

This repo is based on ConvNeXt. We also refer to the repositories CNNSpot、AIGCDetectBenchmark、GenImage and DNF. Thanks for their wonderful works.

Citation

@article{yan2024sanity,
  title={A Sanity Check for AI-generated Image Detection},
  author={Yan, Shilin and Li, Ouxiang and Cai, Jiayin and Hao, Yanbin and Jiang, Xiaolong and Hu, Yao and Xie, Weidi},
  journal={arXiv preprint arXiv:2406.19435},
  year={2024}
}

Contact

If you have any question about this project, please feel free to contact tattoo.ysl@gmail.com.

shilinyan99 / AIDE

readme