Machine and Deep Learning for DDoS Detection

Marcos V. O. Assis ([email protected])

Published Results:

• A GRU deep learning system against attacks in software defined networks

• https://doi.org/10.1016/j.jnca.2020.102942

• *Update - 06/2022 - improved detection results through better data cleaning process. Updated results on Git.

Objectives

1. Evaluate different Machine and Deep Learning methods for anomaly detection.
2. Detection of Distributed Denial of Service Attacks

Dataset

• CIC-DDoS2019 - https://www.unb.ca/cic/datasets/ddos-2019.html

Evaluated Methods

• Gated Recurrent Units (GRU)
• Long-Short Term Memory (LSTM)
• Convolutional Neural Network (CNN)
• Deep Neural Network (DNN)
• Support Vector Machine (SVM)
• Logistic Regression (LR)
• Gradient Descent (GD)
• k Nearest Neighbors (kNN)

Environment Config.

• Python 3.7.13
• Numpy 1.16.4
• Scikit-learn 0.21.2
• Pandas 0.24.2
• Tensorflow 1.14.0
• Keras 2.2.4
• Matplotlib 3.1.0
• Seaborn 0.11.2