303COM: A Deep Learning approach for detecting DDoS attacks

Description

This repository provides the datasets (in .ARFF format) and the trained MODEL files of the Recurent Neural Network - Long Short-Term Memory (LSTM) and Random Forest (RF) that were used to answer the project's research questions.

Contents

• Datasets/CIC-DDoS2019_M.zip

  • Contains the prepared 'CIC-DDoS2019_M' training dataset

• Datasets/CIC-DDoS2019_Test.zip

  • Contains the prepared 'CIC-DDoS2019_Test' evaluation dataset.

• Models/Random Forest.MODEL

  • Contains the trained RF model that was used for this project.

• Models/Deep LSTM.MODEL

  • Contains the trained multiple-layer LSTM model that was used for this project.

References

Sharafaldin, I., Lashkari, A., Hakak, S., and Ghorbani, A. (2019) Developing Realistic Distributed Denial of Service (DDoS) Attack Dataset and Taxonomy. ‘2019 International Carnahan Conference on Security Technology’. held 1-3 October 2019 at Chennai. India: IEEE Press

UNB (2019) DDoS Evaluation Dataset (CIC-DDoS2019) [online] available from < https://www.unb.ca/cic/datasets/ddos-2019.html> [04 March 2021]