Skip to content

Kush05Bhardwaj/AIris-Security_AI-Powered-Vulnerability-Scanner

Repository files navigation

AIris Security

AI-Powered Vulnerability Assessment Platform

Python Next.js License Version


What is AIris Security?

AIris Security is a full-stack vulnerability scanning platform that combines four industry-standard security tools with a hybrid machine-learning engine. Submit a target URL and the platform automatically runs all scanners in parallel, scores the risk with ML, and produces a professional PDF report — no manual configuration required.


How it works

User submits URL
      |
      v
+---------------------------------------+
|  Four scanners run in parallel         |
|  Nmap  Nikto  SSLScan  DirSearch       |
+---------------------------------------+
      |
      v
+---------------------------------------+
|  Hybrid ML engine                      |
|  Random Forest + NLP payload classifier|
|  -> Risk score (0-100)                 |
|  -> Attack type + CVE context          |
|  -> Scanner-evidence risk boosts       |
+---------------------------------------+
      |
      v
+---------------------------------------+
|  PDF report                            |
|  Severity pie chart  |  Risk gauge     |
|  Per-finding remediation advice        |
+---------------------------------------+

Scanners

Scanner Detects
Nmap Open ports, running services, OS fingerprinting
Nikto Web server misconfigs, outdated software, HTTP header issues
SSLScan Weak ciphers, deprecated TLS (1.0/1.1/SSLv3), certificate problems
DirSearch Exposed admin panels, backup files, leaked credentials, .git dirs

All four are auto-detected at startup — if the binary exists on the host, it runs automatically.


Repository layout

AIris-Security/
|-- backend/        FastAPI server, scanner runners, ML service, PDF generator
|-- frontend/       Next.js UI  --  scan form, live log terminal, results and reports
|-- ml/             Model training, dataset pipeline, inference API
|-- ARCHITECTURE.md Full system design and data-flow diagrams
|-- DEPLOYMENT.md   Docker, Railway, Render, Vercel deployment guides
|-- CHANGELOG.md    Version history
`-- LICENSE

Detailed documentation

Area Reference
API routes, scanner setup, environment config backend/README.md
Pages, components, environment variables frontend/README.md
Models, training pipeline, datasets ml/README.md
Full system architecture and data-flow ARCHITECTURE.md

Quick start

Prerequisites: Python 3.10+, Node.js 18+, MongoDB, and at least one scanner (Nmap / Nikto / SSLScan / DirSearch).

1 — Backend

cd backend
python -m venv ../.venv
../.venv/Scripts/activate          # Windows
pip install -r requirements.txt
cp .env.example .env               # fill in MONGO_URI and SECRET_KEY
uvicorn server:app --reload --port 8000

2 — Frontend (new terminal)

cd frontend
npm install
cp .env.local.example .env.local   # set NEXT_PUBLIC_API_URL=http://localhost:8000
npm run dev

Open http://localhost:3000. API docs at http://localhost:8000/api/docs.

For cloud deployment see DEPLOYMENT.md.


Tech stack

Layer Technologies
Backend FastAPI, Motor (async MongoDB), Pydantic, python-jose
ML scikit-learn (Random Forest), TF-IDF + Logistic Regression, joblib
PDF ReportLab, Matplotlib
Frontend Next.js 14, Tailwind CSS, Axios
Scanners Nmap, Nikto, SSLScan / testssl.sh, DirSearch

Safe test targets

scanme.nmap.org          # Nmap official test server
testphp.vulnweb.com      # Acunetix test application
localhost                # Your own services

Warning -- Only scan targets you own or have explicit written permission to scan. Unauthorised scanning is illegal in most jurisdictions.


License

MIT -- see LICENSE.


Last updated: March 2026 -- v2.1.0

About

Building an AI-powered vulnerability scanner — runs Nmap, Nikto, SSLScan & DirSearch in parallel, scores risk with a hybrid ML engine (Random Forest + NLP), and generates PDF reports with remediation advice. Built with FastAPI, Next.js, and MongoDB.

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors