README.md

---
title: Radai Api
emoji: 🧠
colorFrom: blue
colorTo: indigo
sdk: docker
app_file: app.py
pinned: false
---

# 🧠 RADAI — Real-Time AI Image Detection Extension

<div align="center">

**Bringing trust back to the internet — one image at a time.**

[![Status](https://img.shields.io/badge/Status-Working-success?style=for-the-badge)](https://github.com/How2Invade/extension-deepfake)
[![Model](https://img.shields.io/badge/Model-OpenCLIP2-black?style=for-the-badge)](https://github.com/How2Invade/extension-deepfake)
[![Backend](https://img.shields.io/badge/Backend-Flask-blue?style=for-the-badge)](https://flask.palletsprojects.com/)
[![Platform](https://img.shields.io/badge/Platform-Chrome-green?style=for-the-badge)](https://chrome.google.com/)
[![PyTorch](https://img.shields.io/badge/PyTorch-EE4C2C?style=for-the-badge&logo=pytorch&logoColor=white)](https://pytorch.org/)
[![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge&logo=python&logoColor=white)](https://python.org/)

[Report Bug](https://github.com/How2Invade/extension-deepfake/issues) • [Request Feature](https://github.com/How2Invade/extension-deepfake/issues) • [View Demo](#-output)

**Built for Prakalp 4.0**

</div>

---

## ✨ What is AI Detector?

With the explosion of generative AI tools like **Stable Diffusion**, **Midjourney**, and **DALL·E**, distinguishing real images from synthetic ones has become nearly impossible for the human eye.

**RADAI** is a real-time deepfake detection Chrome extension that scans every image on any webpage and classifies it as:

- 🧠 **AI Generated** — flagged with a red border and confidence score
- 📷 **Real** — confirmed with a green border and confidence score

It doesn't just stop there. It calculates a **full page-level risk score** so you can instantly understand how much synthetic content you're being served — on any website, at any time.

> In a world where AI can generate anything — this system helps you understand what is real.

---

## 🚀 Features

### 🔍 Real-Time Image Scanning
- Detects all visible images on any webpage
- Works on Google Images, blogs, news sites, social media — anywhere
- Ignores hidden or non-visible DOM elements for accurate results

### 🎯 AI vs Real Classification
- Powered by **OpenCLIP (ViT-L-14)** & **ConvNeXt-Base** deep vision models
- Transfer learning with a custom binary classification head
- Outputs a clean probability score per image

### 🎨 Visual Highlighting
- 🔴 **Red border** → AI Generated
- 🟢 **Green border** → Real
- Hover over any image to see its label + confidence score

### 📊 Page Risk Analysis
Calculates an overall AI content percentage for the entire page:

| Risk Level | Range | Meaning |
|------------|-------|---------|
| 🟢 Low Risk | 0–30% | Mostly real content |
| 🟡 Moderate Risk | 30–70% | Mixed content |
| 🔴 High Risk | 70–100% | Mostly AI-generated |

### ⚡ Clean UI/UX
- Minimal, Apple-inspired design
- Fast and non-intrusive
- Confidence scores displayed inline

---

## ⚙️ How It Works

### Step 1 — Image Extraction
The extension scans the webpage DOM and collects all visible `<img>` elements, extracting their `src` URLs for backend processing.

### Step 2 — URL-Based Backend Processing
Image URLs are sent directly to the Flask backend — no screenshots, no compression artifacts. This ensures maximum accuracy and faster processing.

### Step 3 — Feature Extraction via OpenCLIP
The backend uses a frozen **OpenCLIP (ViT-L-14)** backbone pretrained on `datacomp_xl_s13b_b90k` to convert each image into rich deep feature embeddings.

### Step 4 — Custom Classification Head
A lightweight neural network processes those embeddings:

```
Linear → ReLU → Dropout → Linear → Sigmoid
```

Output: A probability score indicating how likely the image is AI-generated.

### Step 5 — UI Rendering
Results are pushed back to the extension, which:
- Highlights each image directly on the page
- Overlays confidence labels on hover
- Updates the popup with page-level risk analysis

---

## 🧪 Model Details

| Property | Value |
|----------|-------|
| **Ensemble** | OpenCLIP (ViT-L-14) + ConvNeXt-Base |
| **Pretrained On** | datacomp_xl_s13b_b90k |
| **Approach** | Transfer Learning |
| **Encoder** | Frozen |
| **Head** | Custom Binary Classifier |
| **Output** | AI / Real + Probability |

### 📂 Training Dataset

**AI Images:** Stable Diffusion, Midjourney, DALL·E, Flux

**Real Images:** Unsplash dataset

---

## 🏗 Project Structure

```
extension-deepfake/
│
├── app.py                        # Flask backend — model inference & API
├── OpenCLIP_forensic_head.pth      # Trained model weights
├── train.py                      # Training script (reference only)
│
└── extension/
    ├── manifest.json             # Chrome extension configuration
    ├── popup.html                # Extension UI layout
    ├── popup.js                  # Button logic & UI state updates
    └── content.js                # DOM scanning & image highlighting
```

---

## ⚙️ Setup & Installation

### Prerequisites

- Python 3.8+
- pip
- Google Chrome browser

---

### 1. Clone the Repository

```bash
git clone https://github.com/How2Invade/extension-deepfake.git
cd extension-deepfake
```

---

### 2. Install Backend Dependencies

```bash
pip install torch torchvision flask pillow open_clip_torch
```

---

### 3. Run the Flask Backend

```bash
python app.py
```

The server will start at:

```
http://127.0.0.1:5000
```

> Keep this terminal running while using the extension.

---

### 4. Load the Chrome Extension

1. Open Chrome and navigate to `chrome://extensions/`
2. Toggle **Developer Mode** (top right)
3. Click **Load Unpacked**
4. Select the `extension/` folder from the cloned repo

---

### 5. Start Detecting

1. Open any webpage (try Google Images)
2. Click the **AI Detector** extension icon
3. Hit **Scan Images**

Every image on the page will be analyzed and highlighted instantly.

---

## 🎯 Output

Each scanned image receives:
- A **colored border** (Red = AI, Green = Real)
- A **confidence label** on hover (e.g., `AI — 78%` or `Real — 64%`)

The popup displays:
- Overall **risk percentage**
- Page-level **verdict** (Low / Moderate / High Risk)

---

## 🔮 Future Scope

- 🎥 **Video deepfake detection** — frame-by-frame analysis
- 🎙️ **Audio deepfake detection** — voice synthesis identification
- ☁️ **Cloud deployment** — remove the local backend requirement
- 📊 **Advanced analytics dashboard** — historical scan data & trends
- ⚡ **Batch inference optimization** — faster multi-image processing

---

## ⚠️ Limitations

- Accuracy depends on training data coverage
- Some false positives may occur on heavily stylized images
- Backend must be running locally for the extension to work

---

## 🏆 Impact

AI Detector directly addresses one of the most pressing issues of the AI era:

- ✅ Detecting fake and synthetic content at scale
- ✅ Reducing the spread of AI-powered misinformation
- ✅ Empowering users to verify what they see online
- ✅ Assisting journalists, researchers, and media professionals

---

## 🙏 Acknowledgments

- [OpenCLIP](https://github.com/mlfoundations/open_clip) for the OpenCLIP vision model
- [PyTorch](https://pytorch.org/) ecosystem for model training and inference
- [Chrome Extensions API](https://developer.chrome.com/docs/extensions/) for browser integration
- [Unsplash](https://unsplash.com/) for real image training data

---

<div align="center">

### 💡 Built to bring trust in an AI-generated world

[⭐ Star on GitHub](https://github.com/How2Invade/extension-deepfake) • [🐛 Report an Issue](https://github.com/How2Invade/extension-deepfake/issues)

</div>