ShieldNet

AI-powered cybersecurity dashboard for real-time phishing and malware URL detection.

---

Overview

ShieldNet uses a custom-trained Random Forest classifier (trained on 650k+ URLs, 94% accuracy) to detect malicious URLs in real time. It includes a React dashboard, Chrome extension, scan history, threat logs, and PDF report generation — all backed by a FastAPI + SQLite backend with Google OAuth.

---

Stack

Backend — Python, FastAPI, scikit-learn, SQLAlchemy, SQLite, NumPy, Pandas

Frontend — React 18, TypeScript, Vite, Tailwind CSS, ShadCN UI, Framer Motion, Recharts, TanStack Query

Extension — Chrome Extensions API (Manifest V3)

---

Getting Started

Backend

cd backend
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

Add a .env file to backend/ — see .env.example.

uvicorn app.main:app --reload --port 8000

Train the model

cd backend/ml
# Add your dataset as malicious_phish.csv
python train_model.py

Frontend

cd frontend
npm install
npm run dev

Chrome Extension

Go to chrome://extensions → Enable Developer mode → Load unpacked → select extension/

---

Project Structure

ShieldNet/
├── frontend/        # React + Vite
├── backend/
│   ├── app/         # FastAPI routes, models, auth
│   └── ml/          # Training script + model
└── extension/       # Chrome extension

---

Built by Zoya Khan