Hugging Face's logo

pixelprism-ai
/
dfd-arena-mini

Image Classification
Transformers
Safetensors
swinv2
deepfake-detection
ai-image-detection
dfd-arena
bitmind
Model card Files
xet
 Community
dfd-arena-mini / README.md
kriskraw's picture
kriskraw
Upload README.md with huggingface_hub
ed0c319 verified
preview code
|
raw
history blame contribute delete
3.21 kB
metadata 
license: mit
tags:
  - deepfake-detection
  - ai-image-detection
  - dfd-arena
  - bitmind
library_name: transformers
pipeline_tag: image-classification

PixelPrism v0.1 — DFD Arena Submission

Sanitized single-detector submission for the BitMind Deepfake Detection Arena.

This repo represents the most informative single component of PixelPrism's production V9 16-detector ensemble, wrapped in the BitMind DeepfakeDetector interface so it can be evaluated alongside NPR / UCF / CAMO on the public leaderboard.

What's in this submission

A wrapper around the Swin V2 transformer head (haywoodsloan/ai-image-detector-deploy, MIT licensed). In PixelPrism's V9 permutation-importance audit (8000 samples, 5 reps), Swin V2 ranked #1 by a wide margin at importance 0.271, vs 0.109 for the next-best detector (vit3) and 0.032 for DIRE-FLUX. It alone accounts for ~38% of V9's total discriminative power.

What's NOT in this submission

The full PixelPrism V9 ensemble fuses 16 detectors via a HistGradientBoostingClassifier meta-classifier:

fft, vit, vit2, vit3, dire (SD 1.5), clip, srm, exif, face,
cfa, prnu, c2pa, anatomy, swin, dire_sdxl, dire_flux

Some V9 components depend on weights that are not MIT-redistributable:

  • dire_flux uses FLUX.1-schnell (non-commercial license)
  • dire_sdxl uses Stability SDXL (CreativeML OpenRAIL-M)
  • face uses FaceForensics++ Xception variants (access-gated)

Those stay in our internal production stack rather than the public submission.

Live full-ensemble numbers

The full V9 ensemble is live at https://pixelprism.ai/api/detect (paid) and https://pixelprism.ai/api/scan-public (5/day free tier). Per-generator detection rates and 30-day drift trend are published at https://pixelprism.ai/leaderboard (refreshed monthly with each retrain).

V9 internal holdout (8000 stratified samples, 4000 real / 4000 AI):

Metric V9
Overall 96.7%
Real 96.1%
AI 97.4%
Per-generator min 91.0% (Grok)
Drift gap (fresh AI vs known AI) −2.7pp (fresh AI now BEATS known AI)

Files in this repo

File Purpose
pixelprism_detector.py The DeepfakeDetector subclass registered as PixelPrism in DETECTOR_REGISTRY
pixelprism_config.yaml YAML config with hf_repo, backbone_repo, ai_label_idx
model.safetensors Swin V2 weights (re-hosted, byte-identical to upstream)
config.json Swin V2 model config
preprocessor_config.json Swin V2 image preprocessor config
README.md This file

Citation / contact

If you use this in research or a comparison study, cite:

Operator: Chris Crawley, PixelPrism.ai · https://pixelprism.ai

License

MIT (matches the upstream Swin V2 model + matches the BitMind DFD Arena requirement).