NeuralCTF CyberArena X — Adaptive AI-Powered Cybersecurity Training Simulator
PhantomRange is a futuristic, defensive-focused cybersecurity simulation platform built entirely in Python. It generates dynamic virtual infrastructures, simulates safe educational attack chains, and deploys an AI Defender that adapts in real time. Designed for training, CTF practice, and portfolio demonstration, it delivers a cyberpunk-hacker aesthetic with production-grade architecture.
Developer: issu321
Repository: github.com/issu321/PhantomRange
- 🎯 Adaptive Simulation Engine — Randomized or scenario-based network generation
- 🤖 AI Defender System — scikit-learn powered threat detection with real-time countermeasures
- 🕸️ Interactive Network Graphs — Plotly-powered topology visualization
- ⚔️ Safe Attack Chain Simulation — Educational reconnaissance → exfiltration pipeline
- 📊 Cyberpunk Dashboard — Neon-themed metrics, risk heatmaps, and terminal streams
- 📁 Exportable Reports — JSON session dumps and CSV node inventories
- 🧠 Explainable AI — Feature importance and remediation recommendations
git clone https://github.com/issu321/PhantomRange.git
cd PhantomRange
bash install.shgit clone https://github.com/issu321/PhantomRange.git
cd PhantomRange
install.batThe installer automatically creates a virtual environment, installs dependencies, and launches the Streamlit interface.
- Open the Dashboard from the sidebar
- Select a Scenario (or Random Generation) and Difficulty
- Click Initialize Simulation
- Navigate to Simulation Lab to execute attack phases
- Monitor the AI Defender responses and patch vulnerabilities in Network Graph
- Export reports from the Reports tab
| Phase | Description |
|---|---|
| Reconnaissance | Simulated information gathering |
| Scanning | Port and service enumeration |
| Credential Discovery | Weak credential detection (educational) |
| Privilege Escalation | Simulated access elevation |
| Lateral Movement | Virtual network traversal |
| Data Exfiltration | Sensitive data store discovery |
All phases are sandboxed and simulated. No real exploitation occurs.
- Python 3.11+
- Streamlit — Frontend UI
- Plotly — Interactive visualizations
- NetworkX — Graph topology generation
- scikit-learn — AI defender RandomForest classifier
- NumPy & Pandas — Data processing
- Matplotlib — Static chart exports
PhantomRange/
├── app.py # Main application (backend + frontend)
├── requirements.txt # Python dependencies
├── README.md # Project documentation
├── install.sh # Linux/macOS installer
├── install.bat # Windows installer
├── inputguide.md # Usage guide
├── scenarios.json # Predefined simulation scenarios
├── .gitignore # Git exclusions
└── assets/
└── styles.css # Cyberpunk Streamlit theme
The AI Defender uses a RandomForestClassifier trained on synthetic feature vectors representing:
- Node security level
- Vulnerability count
- Historical alert frequency
- Current attack phase index
When the simulation advances, the model predicts compromise probability per node. If risk exceeds the difficulty-adjusted threshold, the defender triggers actions such as virtual honeypot deployment, quarantine isolation, or authentication hardening.
PhantomRange is a SAFE educational simulation only.
- No real malware is generated
- No actual network exploitation occurs
- All attack chains are abstracted and sandboxed
- Intended for cybersecurity education, CTF training, and defensive skill development
- Plugin system for custom scenarios
- Multiplayer CTF mode via WebSocket
- LLM-powered narrative generation
- MITRE ATT&CK framework mapping
- Docker containerization
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Distributed under the MIT License. See LICENSE for more information.
Developed by issu321