Metadata-Version: 2.1
Name: AutoZeekWatch
Version: 0.1.1
Summary: Network Intrusion Detection using Zeek logs
Home-page: https://github.com/zoe70416/NIDS/
License: MIT
Project-URL: Documentation, https://github.com/zoe70416/NIDS
Project-URL: Bug Reports, https://github.com/zoe70416/NIDS/issues
Project-URL: Source Code, https://github.com/zoe70416/NIDS
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: joblib==1.3.2
Requires-Dist: matplotlib==3.7.0
Requires-Dist: mlflow==2.2.1
Requires-Dist: numpy==1.23.5
Requires-Dist: pandas==1.4.2
Requires-Dist: pyod==1.1.0
Requires-Dist: pysad==0.2.0
Requires-Dist: scikit_learn==1.3.2
Requires-Dist: seaborn==0.11.2
Requires-Dist: tailer==0.4.1
Requires-Dist: combo==0.1.3

# Network Intrusion Detection System (NIDS)

## Purpose
This repository is dedicated to developing a Network Intrusion Detection System (NIDS) utilizing unsupervised machine learning techniques such as KitNET, Autoencoder, and Isolation Forest.

## Data Description
The input data for this system is Zeek conn logs. The data is unstructured, with variations in columns across different instances.

## Code Description

1. **data_preprocess.py:** This script preprocesses data specifically for the KitNET model.
2. **train_kitnet.py:** Contains code for training a KitNET model on HSRN data, using parameters from the best model. Use the argument to specify the date of the data to be trained on, for example, 2023-11-19.
3. **pred_kitnet.py:** This script processes data from the "current" folder, which stores new data, and preprocesses it for the KitNET model.
