Skip to content

100Psycho007/ai-phishing-url-detector

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🛡️ AI Phishing URL Detector (v1)

A browser-based phishing detector that uses image-based classification via Teachable Machine. Upload a screenshot of a website, and this tool will predict if it's Phishing or Safe.


📌 Live Demo

👉 Visit the Live Site


📸 How It Works

  1. Upload a screenshot containing a visible website URL.

  2. A pre-trained MobileNet model (via Teachable Machine) classifies it as:

    • ✅ Safe
    • 🚫 Phishing
  3. Results are displayed instantly on the webpage.

Note: Accuracy depends on the training dataset. This version is a proof-of-concept.


⚙️ Tech Stack

  • HTML, CSS, JavaScript
  • TensorFlow.js
  • Teachable Machine (MobileNet)
  • GitHub Pages for deployment

🗂️ Folder Structure

├── index.html          # UI code
├── model/              # Exported TM model (model.json, metadata.json, weights.bin)
├── docs/               # 📄 Documentation & screenshots (to be added)
├── app/                # (optional) alternate versioning space for future refactor
└── README.md           # You're here

📁 docs/

File Description
screenshots/ UI and sample result images
model-info.md Notes on training params and classes
walkthrough.md Simple usage guide with visuals

📝 To be added by contributor


🚀 How to Use

  1. Go to the Live Demo
  2. Upload a screenshot image
  3. See the prediction result below the image

🧪 Example Screenshots

📍 (Place these in docs/screenshots/)

  • Safe site prediction ✅
  • Phishing site prediction 🚫

📈 Accuracy

This version uses a small dataset with basic image classification.

Model Type Source Notes
MobileNet Teachable Machine Lightweight, fast, less accurate for fine-grained tasks

Known Limitations

  • May misclassify clever phishing designs
  • Cannot analyze URL text deeply
  • Only works with visible screenshots

📦 License

MIT License


🚧 What's Next (v2 Preview)

A smarter hybrid phishing detector with:

  • ✅ OCR (Tesseract.js) to extract URLs
  • ✅ GPT/OpenRouter AI check
  • ✅ VirusTotal API verification

Follow progress in the upcoming smart-phishing-detector repo.


👤 Author

100Psycho007 – Final year BSc Botany + Zoology student interested in AI x Cybersecurity.

About

A no-code machine learning project that detects phishing URLs using an AI model trained via Google AutoML or Teachable Machine.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages