Skip to content
BranchesTags

Repository files navigation

🛡️ SecureID AI

An AI-Powered Digital Identity & Scam Prevention Platform

Know before you click, answer, or pay.

SecureID AI combines phishing detection, QR code analysis, voice scam detection, deepfake detection, identity risk monitoring, and an AI security assistant into a single, unified platform — instead of forcing users to juggle five different single-purpose security tools.

Live Frontend Live Backend License: MIT

📖 Table of Contents

🎯 Problem

People are targeted by scams from every direction, and existing tools only ever solve one piece of the puzzle:

Threat Typical current defense
Phishing websites A browser warning, if you're lucky
QR code scams Nothing — most people scan blindly
Fake customer support calls Nothing, until it's too late
Deepfake videos and voices Almost no consumer-facing tools
Identity theft Reactive, after-the-fact breach alerts
Fake banking / UPI apps App store moderation, which lags
Fraudulent emails and SMS Basic spam filters

Each of these usually requires a separate app or service. SecureID AI brings all of them into one platform, with one consistent, explainable risk score across every check.

💡 Solution

SecureID AI is a single web platform where a user can:

  1. Paste a suspicious link, SMS, or email and get an instant, explained risk score
  2. Scan a QR code before opening whatever it points to
  3. Upload a suspicious call recording and check for scam patterns or voice cloning
  4. Upload a photo or video and check whether it's AI-generated or manipulated
  5. See one overall "digital identity safety score" across passwords, breach exposure, and device hygiene
  6. Ask a plain-language AI assistant, "Is this safe?" — and get reasoning, not just a verdict
  7. Report scams to a community map that helps warn others nearby

✨ Core Features

🔗 AI Phishing Website Detector

Paste a URL → get a 0–100 risk score, a plain-language verdict, and the specific indicators that drove the score (domain age, HTTPS status, brand mimicry, etc.).

📷 QR Code Scanner

Scan or upload a QR code. The decoded destination is always shown before any action is taken, and is then run through the same phishing analysis pipeline.

🎙️ Voice Scam Detection

Upload or record a suspicious call. The AI transcribes it, highlights scam-pattern phrases inline, and flags whether the voice shows signs of AI cloning.

🎭 Deepfake Image & Video Detection

Upload a photo or video and get a confidence score for AI-generation/manipulation, with visual indicators on the flagged regions or frames.

📊 Identity Risk Dashboard

One overall safety score built from password strength, email breach exposure, and a self-reported device security checklist — with prioritized, actionable recommendations.

💬 AI Chat Security Assistant

Ask natural questions like "Is this SMS a scam?" or "Can I trust this website?" — the assistant reasons through it in plain language and can trigger a full formal scan inline.

🌐 Scam Reporting Network

Report scams, browse a community map of scam hotspots, and help protect others nearby.

🎬 Demo

End-to-end scenario:

User receives a suspicious SMS
        │
        ▼
Pastes it into the Assistant → AI flags phishing language + urgency
        │
        ▼
Scans the QR code inside the message → destination confirmed unsafe
        │
        ▼
Uploads the follow-up scam call → AI flags likely scam attempt
        │
        ▼
Dashboard recommends: block the sender, report the scam

🔗 Live app: secure-id-ai.vercel.app 🔗 API docs (Swagger UI): secureid-ai-backend.onrender.com/docs

⚠️ The backend runs on a free-tier instance and may take up to 50 seconds to wake up on the first request after inactivity.

🧰 Tech Stack

Frontend

  • React / Vite + TypeScript
  • Tailwind CSS

Backend

  • FastAPI (Python)

AI / ML

  • Gemini / OpenAI API
  • Hugging Face models
  • OCR — EasyOCR / Tesseract
  • XGBoost / Random Forest (phishing scoring)
  • NLP classifiers (scam text detection)

Data

  • PostgreSQL
  • Redis (caching, job queue)

Auth

  • Firebase Authentication

Infrastructure

  • Docker
  • GitHub Actions (CI/CD)
  • Render (backend + database hosting)
  • Vercel (frontend hosting)

🏗️ Architecture

                     User
                       │
                       ▼
              React (Vite) Web App
                       │
                       ▼
               FastAPI Backend
                       │
   ┌───────────┬───────┼───────┬───────────┬────────────┐
   ▼           ▼       ▼       ▼           ▼            ▼
Phishing   Scam Text  Voice  Deepfake     QR       Identity Risk
Detection  Classifier Analysis Detection Analyzer      Engine
   │           │       │       │           │            │
   └───────────┴───────┴───┬───┴───────────┴────────────┘
                            ▼
                     PostgreSQL + Redis

See the full Backend PRD and Database Schema PRD for the detailed service and data model.

📁 Project Structure

SecureID-AI/
├── backend/                 # FastAPI application
│   ├── app/
│   │   ├── api/v1/endpoints/  # Route handlers (scan, auth, identity, reports, assistant, history)
│   │   ├── core/               # Config, database, security
│   │   ├── models/              # SQLAlchemy models & Pydantic schemas
│   │   └── services/             # AI/ML and forensic analysis services
│   ├── requirements.txt
│   └── main entrypoint: app/main.py
├── src/                     # React (Vite) frontend source
├── public/                  # Static assets
├── docs/                    # PRDs and planning documents
├── .gitignore
├── package.json
├── vite.config.ts
└── README.md

🚀 Getting Started

Prerequisites

  • Node.js 18+
  • Python 3.10+
  • PostgreSQL (local or hosted)
  • API keys: Gemini/OpenAI, Firebase project credentials

1. Clone the repository

git clone https://github.com/asadullatariq123/SecureID-AI.git
cd SecureID-AI

2. Frontend setup

npm install
npm run dev

The app runs at http://localhost:5173 by default.

3. Backend setup

cd backend
python -m venv .venv
.venv\Scripts\activate        # Windows
# source .venv/bin/activate   # macOS/Linux

pip install -r requirements.txt
uvicorn app.main:app --reload

The API runs at http://localhost:8000, with interactive docs at http://localhost:8000/docs.

4. Set up environment variables

Copy .env.example → .env in both the root and backend/ folders, and fill in your own values (see below).

🔑 Environment Variables

Backend (backend/.env)

DATABASE_URL=postgresql://user:password@host/dbname
GEMINI_API_KEY=your_gemini_api_key
OPENAI_API_KEY=your_openai_api_key
FIREBASE_PROJECT_ID=your_firebase_project_id

Frontend (.env)

VITE_API_URL=http://localhost:8000
VITE_FIREBASE_API_KEY=your_firebase_api_key
VITE_FIREBASE_AUTH_DOMAIN=your_firebase_auth_domain

Never commit real .env files. Only commit .env.example with placeholder values.

☁️ Deployment

Layer Platform Notes
Frontend Vercel Auto-deploys from main, root directory ., Vite framework preset
Backend Render Auto-deploys from main, root directory backend, start command uvicorn app.main:app --host 0.0.0.0 --port $PORT
Database Render PostgreSQL Connected via DATABASE_URL env var

Every push to main automatically redeploys both the frontend and backend — no manual steps required after initial setup.

🗺️ Roadmap

  • Browser extension for real-time phishing alerts
  • Native mobile app
  • Enterprise dashboard for organizations
  • Bank API integration
  • Digital identity wallet
  • Family protection mode for children and older adults

🤝 Contributing

Contributions are welcome. To contribute:

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/your-feature)
  3. Commit your changes (git commit -m "Add your feature")
  4. Push to the branch (git push origin feature/your-feature)
  5. Open a Pull Request

Please open an issue first for major changes so we can discuss what you'd like to change.

📄 License

This project is licensed under the MIT License.

👥 Team

  • V.A. Asadulla Tariq
  • G.K. Hemashankar
  • G. Kavya Reddy
  • S. Mounika

Built as a hackathon project focused on AI-powered scam prevention and digital safety.

Made with care to help people stay safe online — one scam check at a time.

About

secure-id-ai.vercel.app

Resources

Readme
Activity

Stars

0 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases

Packages

Contributors

Languages