Skip to content

uozkl/Machine-Learning-DDoS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Machine-Learning-DDoS

CSI4900 Project, DDoS detection using machine learning

Features

Detect DDoS attack traffic using a machine learning method.
Giving network traffic of a period and tells whether the remote host is committing DDoS attack.

Directory layout

Machine-Learning-DDoS
├── data                   # Dataset
│   └── processed          # Processed data for the score
│   └── raw                # Raw unprocessed data
├── docs                   # Documentation
├── models                 # Trained classifiers
├── references             # Reference papers
└── src                    # Source files
    └── process            # Preprocess classes
    └── score              # Class to generate accuracy of 5 selected classifiers

Dataset

CICDDoS2019 from UNB
This dataset provides a large set of attack traffic with different types, the type of attack was labeled in the CSV file.
In Github, only first 200k records of each type of attack were uploaded. Rest of the data could be downloaded from the link of the dataset.

Type of attack

In the dataset, the following types of DDoS were provided.
DNS, LDAP, MSSQL, NetBIOS, NTP, PortMap, SNMP, SSDP, SYN, TFTP, UDP, UDP-Lag

Training method(Techniques)

Multilayer Perceptron, random forest, Naive Bayes, K-nearest neighbors

About

CSI4900 Project, DDoS detection using machine learning

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages