🕵️♂️ ERASE: Bypassing Collaborative Detection of AI Counterfeit (Model Weights)
Qianyun Yang1
Peizhuo Lv2
Yingjiu Li3
Shengzhi Zhang4
Yuxuan Chen1
Zixu Li1
Yupeng Hu1
1Shandong University
2Nanyang Technological University
3University of Oregon
4Boston University
These are the official pre-trained model weights for **ERASE**, an optimization framework designed to bypass single and collaborative detection of AI-Generated Images (AIGI) by comprehensively eliminating multi-dimensional generative artifacts.
🔗 **Paper:** [Accepted by IEEE TDSC 2026] (Coming Soon)
🔗 **GitHub Repository:** [iLearn-Lab/TDSC26-ERASE](https://github.com/iLearn-Lab/TDSC26-ERASE)
---
## 📌 Model Information
### 1. Model Name
**ERASE** (comprehensive counterfeit ArtifactS Elimination) Checkpoints.
### 2. Task Type & Applicable Tasks
- **Task Type:** Adversarial Attack / AI-Generated Image Stealth (AIGI-S) / Image-to-Image
- **Applicable Tasks:** Bypassing AI-generated image detectors (both single detectors and collaborative multi-detector environments) while maintaining exceptionally high visual fidelity.
### 3. Project Introduction
With the rapid development of generative AI, the issue of deepfakes has become increasingly severe. Existing AI-Generated Image Stealth (AIGI-S) methods typically optimize against a single detector and often fail when facing real-world "Collaborative Detection". Moreover, they often introduce obvious artifacts visible to human observers.
**ERASE** is a stealth optimization framework that innovatively combines:
- 🎯 **Sensitive Feature Attack**
- ⛓️ **Diffusion Chain Attack** (Optimization-free)
- 📻 **Decoupled Frequency Domain Processing**
This Hugging Face repository hosts the pre-trained weights required to run the Decoupled Frequency Domain Processing and the Surrogate Classifiers, specifically `noise_prototype_VAE.pt`, `dncnn_color_blind.pth`, and the `ckpt_ori` surrogate weights.
### 4. Training Data Source
The surrogate classifiers and related components were primarily trained and evaluated on the **[GenImage](https://github.com/GenImage-Dataset/GenImage)** dataset, following the standard task settings of AIGI-S evaluation.
---
## 🚀 Usage & Basic Inference
These weights are designed to be used seamlessly out-of-the-box with the official ERASE GitHub repository.
### Step 1: Prepare the Environment
Clone the GitHub repository and install dependencies:
```bash
git clone https://github.com/iLearn-Lab/TDSC26-ERASE
cd ERASE
conda create -n erase python=3.9 -y
conda activate erase
pip install -r requirements.txt
```
### Step 2: Download Model Weights
Download the files from this Hugging Face repository (`ckpt_ori` folder, `noise_prototype_VAE.pt`, `dncnn_color_blind.pth`) and place them in the `checkpoints/` directory of your cloned GitHub repo. Your structure should look like this:
```text
ERASE/
└── checkpoints/
├── ckpt_ori/ # Surrogate model weights (E/R/D/S)
├── noise_prototype_VAE.pt # Frequency VAE weights
└── dncnn_color_blind.pth # Denoising/Frequency weights
```
### Step 3: Run the Attack
Use `main.py` from the code repository to perform basic inference and generate adversarial images:
```bash
python main.py \
--images_root ./input_images \
--save_dir ./output \
--model_name E,R,D,S \
--diffusion_steps 20 \
--start_step 18 \
--iterations 10 \
--is_encoder 1 \
--encoder_weights ./checkpoints/noise_prototype_VAE.pt \
--eps 4 \
--batch_size 4 \
--device cuda:0
```
---
## ⚠️ Limitations & Notes
**Disclaimer:** This tool and its associated model weights are strictly intended for **academic research, AI security evaluation, and robustness testing**.
- It is strictly **prohibited** to use this repository for any malicious forgery, fraud, or other illegal/unethical purposes.
- Users bear full legal responsibility for any consequences arising from improper use.
---
## 📝⭐️ Citation
If you find our weights or code useful for your research, please consider leaving a **Star** ⭐️ on our GitHub repo and citing our paper:
```bibtex
@article{yang2026erase,
title={ERASE: Bypassing Collaborative Detection of AI Counterfeit via Comprehensive Artifacts Elimination},
author={Yang, Qianyun and Lv, Peizhuo and Li, Yingjiu and Zhang, Shengzhi and Chen, Yuxuan and Chen, Zhiwei and Li, Zixu and Hu, Yupeng},
journal={IEEE Transactions on Dependable and Secure Computing},
year={2026},
publisher={IEEE}
}
```