---
license: other
license_name: polyform-noncommercial-1.0.0
license_link: https://polyformproject.org/licenses/noncommercial/1.0.0
tags:
  - deepfake-detection
  - ensemble
---

# DeepSafe Ensemble Artifacts

The meta-learners that turn 19 individual detector scores into one calibrated
verdict, for [DeepSafe](https://github.com/deepsafehq/deepsafe-bench).

Unlike the model code and weights in the other DeepSafe repositories, **these
are first-party**: trained by us, licensed PolyForm Noncommercial 1.0.0, same
as the project.

## Contents

| Modality | Meta-learner | Held-out AUC |
|---|---|---|
| Image | LightGBM over 7 models | 0.9466 |
| Audio | Random Forest over 3 models | 0.8290 |
| Video | XGBoost over 9 models | 0.6694 |

Each modality ships four files:

- `<modality>_meta_learner.pkl` — the trained model
- `<modality>_scaler.pkl` — feature scaling
- `<modality>_calibrator.pkl` — Platt calibration, so scores read as probabilities
- `<modality>_config.json` — feature order and fallback weights

Trained on the 15,499-sample medium evaluation tier. Without these, the
inference server produces per-model scores but no ensemble verdict.

## Usage

`setup.sh` fetches these automatically. Manually:

```python
from huggingface_hub import snapshot_download
snapshot_download("deepsafe/ensemble", local_dir="models/ensemble/artifacts")
```

## The numbers are the point

Held-out video AUC is **0.6694**. That is barely above chance on generators the
models were not trained for, and it is lower than the cross-validated figure
produced during training. We publish the held-out number because the gap
between the two is the finding. See
[BENCHMARK.md](https://github.com/deepsafehq/deepsafe-bench/blob/main/BENCHMARK.md).

## Security note

These are Python pickles, which execute code on load. Only load them from a
source you trust. DeepSafe's loader refuses any pickle outside its configured
artifacts directory, but that is a guardrail, not a guarantee. If you are
security-sensitive, retrain your own with `deepsafe fit --tier 1`.