README.md

---
license: cc-by-nc-4.0
library_name: sklearn
tags:
  - ai-image-detection
  - stable-diffusion
  - clip
  - denoising-trajectory
  - zero-shot
pipeline_tag: image-classification
---

# Bot or Not — Denoising Trajectory Detector

Logistic-regression classifier on top of denoising-trajectory features extracted
with CLIP ViT-L/14 + Stable Diffusion v1.5. Reproduces the method from
**Liang et al., "Denoising Trajectory Biases for Zero-Shot AI-Generated Image Detection"** (NeurIPS 2025).

## How it works

For each input image:
1. Encode to SD v1.5 latent space (VAE).
2. Add DDPM noise at timesteps `(50, 150, 300, 500, 800)`.
3. Run one UNet denoising step per timestep with an empty-prompt embedding.
4. Decode each denoised latent back to image space.
5. Compute CLIP-cosine similarity between the original and each reconstruction.

This yields a 6-D feature vector `[sim_mean, sim_t50, sim_t150, sim_t300, sim_t500, sim_t800]`,
which a logistic regression (`class_weight='balanced'`, `solver='lbfgs'`) classifies as AI / Real.

## Training data

- **AI images:** 2,500 images generated by diffusion models (1024×1024).
- **Real images:** 2,500 images sampled from COCO 2017 `train2017`.
- 80/20 stratified split, `random_state=42`.

## Test metrics

Held-out test set: 1,000 images (500 Real, 500 AI), `random_state=42`.

| Metric   | Value  |
|----------|--------|
| Accuracy | 0.7940 |
| ROC AUC  | 0.8679 |
| F1       | 0.7876 |

Per-class breakdown:

|       | Precision | Recall | F1   | Support |
|-------|-----------|--------|------|---------|
| Real  | 0.78      | 0.82   | 0.80 | 500     |
| AI    | 0.81      | 0.76   | 0.79 | 500     |

Confusion matrix (rows = true, cols = predicted):

|            | Pred Real | Pred AI |
|------------|-----------|---------|
| True Real  | 412       | 88      |
| True AI    | 118       | 382     |

## Usage

```python
from huggingface_hub import hf_hub_download
import joblib, json
# Or use the bundled inference module:
# from inference import BotOrNotDetector
# detector = BotOrNotDetector.from_pretrained("bezand/BoN1")
# detector.predict("image.jpg")
```

A CUDA GPU is required for practical inference (~30s/image on a T4; CPU inference
is impractical because each prediction runs five SD denoising steps).

## Files

- `classifier.joblib` — trained `sklearn.linear_model.LogisticRegression`.
- `scaler.joblib` — `StandardScaler` fit on training features.
- `config.json` — feature-extractor config (timesteps, CLIP and SD model IDs).
- `inference.py`, `feature_extractor.py` — inference wrappers.

## Limitations and biases

- Trained on a single AI-image source at fixed 1024×1024 resolution. Real images
  (COCO) vary in size and content, which may bias the classifier toward
  resolution/aspect-ratio cues rather than denoising-trajectory artefacts.
- Single-step denoising with an empty prompt; full multi-step trajectories may
  give cleaner signal but were not used in training.
- Only tested against SD-family generators. Performance on other generators
  (Midjourney, FLUX, autoregressive models) is unknown.

## License

The trained classifier weights and `StandardScaler` are released under CC-BY-NC-4.0.
**Inference also requires Stable Diffusion v1.5** (CreativeML Open RAIL-M) and
**CLIP ViT-L/14**, each governed by its own license.

## Citation

```bibtex
@inproceedings{liang2025denoising,
  title  = {Denoising Trajectory Biases for Zero-Shot AI-Generated Image Detection},
  author = {Liang et al.},
  booktitle = {NeurIPS},
  year   = {2025}
}
```