Upload 9 files

README.md

@@ -1,3 +1,127 @@
----
-license: apache-2.0
----
+
+---
+license: apache-2.0
+tags:
+- adversarial-attack
+- ai-generated-image-stealth
+- deepfake-evasion
+- pytorch
+---
+
+<a id="top"></a>
+<div align="center">
+  <h1>🕵️‍♂️ ERASE: Bypassing Collaborative Detection of AI Counterfeit (Model Weights)</h1>
+
+<p>
+    <b>Qianyun Yang</b><sup>1</sup>&nbsp;
+    <b>Peizhuo Lv</b><sup>2</sup>&nbsp;
+    <b>Yingjiu Li</b><sup>3</sup>&nbsp;
+    <b>Shengzhi Zhang</b><sup>4</sup>&nbsp;
+    <b>Yuxuan Chen</b><sup>1</sup>&nbsp;
+    <b>Zixu Li</b><sup>1</sup>&nbsp;
+    <b>Yupeng Hu</b><sup>1</sup>
+  </p>
+
+  <p>
+    <sup>1</sup>Shandong University&nbsp;
+    <sup>2</sup>Nanyang Technological University&nbsp;
+    <sup>3</sup>University of Oregon&nbsp;&nbsp
+    <sup>4</sup>Boston University
+  </p>
+</div>
+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}
+}
+```

ckpt_ori/Controlvae.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b51b0a63b7e6ad7c687d2d3f09300bdabce2b5e29b7991d3c8ca830fe59495
+size 153809053

ckpt_ori/deit.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022df4c37288fb1553ddd76ca8097b20ac5e7670bda20982792c308aee0af4a8
+size 1029776705

ckpt_ori/efficientnet-b0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aaa7f97deb2cc13a20c9c6c6628fbe04a794319ce2ea02438738eb69b4207a9
+size 48584630

ckpt_ori/resnet50.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b154169983ff92980d05e5374dd107d2e9c9fee32264d23afbf5daa6372fb7a
+size 282574075

ckpt_ori/swin-t.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e50469ee6d9fbf9e19fbc0d8fd2829f83c062cb78ca4ede82bba7056fabaf456
+size 1042919826

ckpt_ori/swin_base_patch4_window7_224_22kto1k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5348473e69277d69db915362bef760b5fd04362057bd59c7fe064d431532eab
+size 352792251

dncnn_color_blind.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe11a6b703304df82cdf236f431fc6492766c7b9119d97e943edeb392c710a3
+size 2678121

noise_prototype_VAE.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a664c55fcac4a8905c69677dd5348a2d6838b393c3bb0101e812b1caa1a3fde
+size 602895