Skip to content
This repository has been archived by the owner on Jan 16, 2023. It is now read-only.

luks-m/Intrusion-detection-with-machine-learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

42 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Time series learning applied to intrusion detection in IT systems

Table of content

Description

This project is a 2nd year engeneering school internship project at the University Of Québec in Outaouais.
The purpose was to search and developp a program to code a neural network to learn time series in order to automate the sort of security alerts in a network.

Report

You can access and read my final report in the folder report.

Requirements

To install all required libraries, go to project root and run:

$ pip install -r requirements.txt

Project

Network logs classification

To execute the logs classification, go to src/Intrusion-Detection-NSL-KDD/ folder.
Then, use the command :

$ python3 attack_classification.py

Text prediction

To execute the text prediction, go to src/Word-Prediction folder.
Then, use this command to fit the model :

$ python3 text_precition.py

Then, use this command to test it :

$ python3 newt_word.py

You have to enter 4 words in order to predict the fifth one.

Learning finite state machine

To execute the text prediction, go to src/Finite-State-Machine folder.
Then, use this command to fit the model :

$ python3 neural_network.py

Then, use this command to test it :

$ python3 test_prediction.py

Cybersecurity automation

To execute the text prediction, go to src/Final-Project folder.
Then, use this command to fit the model :

$ python3 lstm.py

Authors

License: MIT
MIT License - Copyright (c) 2022 Lucas MARAIS