AdamAI-Systems — Cybersecurity

Building AI-driven cybersecurity systems that detect, analyze, and respond to network threats. This repository houses the network-security, intrusion-detection, and anomaly-analysis solutions developed by AdamAI-Systems.

Projects in this Repository

1. Network Anomaly / Intrusion Detection (Scapy + PyTorch DNN)

A two-stage pipeline for detecting anomalies and intrusions in live network traffic.

• Tech Stack: Python, Scapy, PyTorch, Pandas, Scikit-learn.
• Key Features:
  • Packet sniffing with scapy — extracts 15 KDD-style session features (src_bytes, dst_bytes, protocol_type, service, flag, count, serror_rate, …) and exports them to CSV.
  • DNN classifier (PyTorch) with BatchNorm + Dropout + ReLU layers, classifying traffic as normal or anomaly.
  • Pretrained weights (mymodel.pth) and a sample features CSV are included for immediate inference.

---

Setup & General Instructions

To run any of the projects locally, navigate to the specific project directory and follow the instructions in its respective README.md.

Most projects follow a common workflow:

1. Create a virtual environment (python -m venv .venv) and activate it.
2. Install dependencies: pip install torch pandas scikit-learn scapy.
3. Run the entry-point script (e.g. python main.py for inference, or python load_data.py for live capture).

Note: Live packet capture with scapy typically requires:

• Running the terminal as Administrator (Windows) or sudo (Linux/macOS).
• Npcap installed on Windows.

---

© 2026 AdamAI-Systems. All rights reserved.