---
title: Deepfake Detector
emoji: 🔍
colorFrom: purple
colorTo: blue
sdk: gradio
sdk_version: 6.9.0
app_file: app.py
pinned: false
---

# Deepfake Face Detector

A hybrid CNN model for detecting AI-generated (deepfake) face images, built using transfer learning on a dual-stream architecture.

## Model Architecture

- **Spatial Stream** — EfficientNet-B4 pretrained on ImageNet, detects visible artifacts
- **Frequency Stream** — Xception + SRM filters, detects invisible GAN noise fingerprints
- **Fusion Module** — Concatenates both streams (3840 features) into a classification head
- **Output** — Sigmoid probability (0 = fake, 1 = real)

## Performance

| Metric | Score |
|--------|-------|
| Test Accuracy | 98.59% |
| Validation Accuracy | 98.55% |

## Dataset

Trained on [140k Real and Fake Faces](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces) — 100k training images, balanced real/fake split.

## Limitations
- Optimized for StyleGAN2 generated faces
- Best results on frontal face images
- Not tested on video deepfakes