Projects 项目展示
MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning
A data-and-model framework for trustworthy medical deepfake detection, built around evidence-grounded reasoning, forgery localization, and a public demo stack.
What is included
- ACL 2026 main conference paper on interpretable medical forgery detection
- MedForge-90K dataset: 30K real images, 30K lesion implant forgeries, and 30K lesion removal forgeries
- MedForge-Reasoner: a Qwen3-VL based detector using a Localize-then-Analyze reasoning pipeline
- Interactive demo for medical image deepfake detection and reasoning visualization
Why it matters
- Moves beyond black-box real/fake prediction to localized, evidence-grounded explanations
- Targets realistic lesion implantation and removal risks in chest X-ray, brain MRI, and fundus images
- Combines dataset, model, and demo into a single research artifact instead of a paper-only release
Public resources
| Asset | Details |
|---|---|
| Paper | ACL 2026 Main Conference |
| Dataset | MedForge-90K, covering CT, MRI, and X-ray with 19 lesion types |
| Model | MedForge-Reasoner on Hugging Face |
| Demo | Online detector Space for interactive testing |
Med-Banana-50K: Large-Scale Medical Image Editing Dataset
A comprehensive 50K-image dataset for instruction-based medical image editing spanning three modalities and 23 disease types.
Key Features
- 50,635 successful edits across 3 medical imaging modalities
- Chest X-ray: 12 pathology types (Pneumothorax, Pleural Effusion, etc.)
- Brain MRI: 4 tumor types (Glioma, Meningioma, Pituitary)
- Fundus photography: 7 disease types (Diabetic Retinopathy, Glaucoma, etc.)
- Bidirectional editing: lesion addition and removal
- LLM-as-Judge quality control with medically grounded rubric
- 37K failed attempts with full conversation logs for preference learning
Dataset Statistics
| Modality | Task | Diseases | Success | Failed |
|---|---|---|---|---|
| Chest X-ray | Add | 12 | 9,854 | 7,971 |
| Chest X-ray | Remove | 12 | 10,667 | 4,750 |
| Brain MRI | Add | 4 | 4,536 | 8,630 |
| Brain MRI | Remove | 4 | 4,355 | 6,949 |
| Fundus | Add | 7 | 18,505 | 3,162 |
| Fundus | Remove | 7 | 2,718 | 6,360 |
| Total | 23+ | 50,635 | 37,822 | |
Note: Full dataset will be released on Hugging Face upon paper acceptance.
DivScore: Zero-Shot LLM Detection in Specialized Domains
A zero-shot detection framework for identifying LLM-generated text in specialized domains like medicine and law, using normalized entropy-based scoring and domain knowledge distillation.
Key Innovations
- Zero-shot detection: No training data required for new domains
- Normalized entropy scoring: Robust metric for specialized text
- Domain knowledge distillation: Leverages domain-specific patterns
- Cross-domain robustness: Tested on medical, legal, and financial texts
Performance Highlights
| Metric | Improvement |
|---|---|
| AUROC | +14.4% vs. SOTA |
| Recall @ 0.1% FPR | +64.0% vs. SOTA |
| Zero-shot Capability | No training needed |
Applications
- Detecting AI-generated medical content to combat misinformation
- Verifying authenticity of legal documents and contracts
- Ensuring integrity in academic and scientific publishing
- Quality control for financial reports and analysis
