VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/1725
Title: | DDoS attacks detection with the use of data mining algorithms | Authors: | Nguyen Ba Le | Keywords: | Distributed denial of service;Data mining;Random forrest;Naive bayes;Logistic regression;Multi-Layer perceptron | Issue Date: | 2023 | Abstract: | Distributed Denial of Service, also called DDoS for short, is well recognized as a prevalent form of cyber attack. Numerous approaches and solutions have been devised to address DDoS attacks. The utilization of data mining methodologies and algorithms has facilitated researchers in extracting valuable information and identifying patterns from extensive datasets, hence enhancing the precision and efficiency of classification tasks. Our goal in this thesis is to leverage various machine learning algorithms for classifying network traffic data into two categories: ”Benign” or ”DDoS”. As well as evaluating the results of these algorithms based on time cost, accuracy, F1, recall, and precision score in order to find the best overall performing algorithm. This paper encompasses a comprehensive depiction of the CICIDS2017 dataset, which serves as the dataset for the data mining task. Additionally, we will give a discussion of the data pre-processing, and feature selection techniques employed in this study, along with a comprehensive overview of DDoS attacks. We utilize Random Forest, Naive Bayes (Multinomial and Gaussian), Logistic Regression, and Multi-Layer Perceptron (MLP) algorithms implemented in Python on the Google Colaboratory platform for this study. |
URI(1): | https://epub.vgu.edu.vn/handle/dlibvgu/1725 | Rights: | Attribution-NonCommercial 4.0 International |
Appears in Collections: | Computer Science (CS) |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
DDoS Attacks Detection with The Use of Data Mining Algorithms.pdf | 2.11 MB | Adobe PDF |
Page view(s)
20
checked on May 29, 2024
Download(s)
10
checked on May 29, 2024
Google ScholarTM
Check
This item is licensed under a Creative Commons License