Skip to content

Latest commit

 

History

History
66 lines (45 loc) · 3.14 KB

README.md

File metadata and controls

66 lines (45 loc) · 3.14 KB

DEEP Open Catalogue: Massive Online Data Streams

Build Status

This work challenges proactive network monitoring for security and protection of computing infrastructures. The principle of the anomaly detection for security lies in proactive prediction from time-series using prediction models based on artificial neural networks, concretely deep learning models. These models are capable to predict next step(s) in near future based on given current and past steps. The intelligent module is built as a machine learning application leveraging deep learning modeling in order to enhance functionality of intrusion detection system (network IDS) supervising network traffic flows.

DEEP Open Catalog entry: DEEP Open Catalog

Project: This work is a part of the DEEP Hybrid-DataCloud project that has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 777435.

Documentation

The documentation of the work is hosted on Read the Docs.

Quickstart

To start using this framework run:

git clone https://github.com/deephdc/mods
cd mods
pip install -e .

Requirements:

  • This project has been tested in Ubuntu 18.04 with Python 3.6.
  • Further package requirements are described in the requirements.txt file.

References:

G. Nguyen, S. Dlugolinsky, V. Tran, A. Lopez Garcia: Deep learning for proactive network monitoring and security protection. IEEE Access, Special section on Deep learning: security and forensics research advances and challenges, Volume 8, Issue 1, pp. 19696-19716, ISSN 2169-3536, DOI 10.1109/ACCESS.2020.2968718, 2020.

G. Nguyen, S. Dlugolinsky, M. Bobak, V. Tran, A. Lopez Garcia, I. Heredia, P. Malik, L. Hluchy: Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a survey. Artificial Intelligence Review, Springer Nature, 2019, ISSN 0269-2821, DOI 10.1007/s10462-018-09679-z

More references

Workflow

Data Preprocessing module

  1. Data cleaning and filtering, feature extraction
  2. Data transformation, ML/DL datapool creation
  3. Feature selection

Deep Learning module (MODS)

  1. Configuration setting
  2. Model training
  3. Model testing

Project organization

  1. The package is built based on DEEP DS template. #cookiecutter #datascience
  2. Prediction and train throught DEEPaaS API