Skip to content

This project implements an AI-powered URL Phishing Detection System that classifies URLs as benign, phishing, or malware using machine learning. It extracts key features from URLs such as length, special characters, domain patterns, and more. A trained model predicts whether a URL is safe or suspicious. integrated with tampermonkey extension

License

Notifications You must be signed in to change notification settings

AbhinashRao/AI_Powered_URL_Phishing_Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🛡️ AI-Powered URL Phishing Detection System – TrustLink

TrustLink is an AI-powered phishing and malware detection system that classifies URLs as benign, phishing, malware, or defacement using both static analysis and dynamic machine learning models. It integrates seamlessly with a browser extension (Tampermonkey) to offer real-time alerts, blocking known malicious URLs and analyzing unknown ones on the fly.


📌 Project Overview

TrustLink combines:

  • 📊 Static analysis of URL patterns, length, and hostnames
  • 🤖 Dynamic analysis using a pre-trained Transformer model
  • 🧩 Tampermonkey browser extension for real-time threat detection
  • 🖥️ Streamlit web app for interactive classification
  • 🔗 Flask backend API for classification engine

🛠️ Technology Stack

Component Technologies Used
🔧 Backend Flask (Python)
🧠 ML Model HuggingFace Transformers (Pre-trained Text Classifier)
🌐 Frontend Streamlit
🧩 Browser Add-on Tampermonkey (JavaScript)
📦 Language Python, JavaScript

🚀 Workflow

  1. 🔗 User Input

    • Enter a URL into the Streamlit web app or use the Tampermonkey extension.
  2. 🧩 Static Analysis

    • Checks against known malicious domain lists and URL patterns.
  3. 🤖 Dynamic Analysis

    • Uses a Transformer-based ML model to classify unknown URLs.
  4. 🧾 Output

    • Classifies as Phishing, Malware, Benign, or Defacement
    • Displays confidence score and logs the event.

📁 Project Structure

AI-URL-Phishing-Detection/
│
├── flask_api.py             # Flask backend API
├── streamlit_app.py         # Streamlit frontend
├── tampermonkey_script.js   # Tampermonkey browser extension
├── model/                   # Pre-trained ML model
├── data/                    # Host lists / datasets
├── requirements.txt         # Python dependencies
├── README.md                # This file
└── ...
💻 Getting Started
🔧 Installation

git clone https://github.com/AbhinashRao/AI-URL-Phishing-Detection.git
cd AI-URL-Phishing-Detection
pip install -r requirements.txt

▶️ Run the Application
1. Start the Flask API:

python flask_api.py
2. Start the Streamlit App:

streamlit run streamlit_app.py
Then open the local Streamlit URL (typically http://localhost:8501) in your browser.

🧩 Browser Extension (Tampermonkey)
Install Tampermonkey extension on your browser.

Import tampermonkey_script.js into Tampermonkey.

When browsing, it will auto-analyze URLs and show alerts for unsafe links.

🧪 Future Enhancements
🔍 Protection against Typosquatting and Homograph attacks

⏳ Include Whois lookup, domain age, and other metadata

🔁 Real-time log storage and dashboard for administrators

🙋‍♂️ Author
Abhinash Rao Madikonda
📧 [email protected]
🔗 LinkedIn • GitHub

About

This project implements an AI-powered URL Phishing Detection System that classifies URLs as benign, phishing, or malware using machine learning. It extracts key features from URLs such as length, special characters, domain patterns, and more. A trained model predicts whether a URL is safe or suspicious. integrated with tampermonkey extension

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published