ITM Web Conf.
Volume 56, 2023First International Conference on Data Science and Advanced Computing (ICDSAC 2023)
|Number of page(s)||8|
|Section||Machine Learning & Neural Networks|
|Published online||09 August 2023|
Improved Intrusion Detection System That Uses Machine Learning Techniques to Proactively Defend DDoS Attack
Department of Computer Science and Engineering, Rajalakshmi Institute of Technology, Chennai, India
This abstract aims to provide a comprehensive analysis of the intricacies of DDoS attacks, which are increasingly prevalent and malicious cyber-attacks that disrupt the normal flow of traffic to a targeted server by exponentially increasing network traffic. To secure distributed systems against DDoS attacks, intrusion detection mechanisms and machine learning techniques are commonly employed. The CICDDoS2019 dataset is often utilized for the detection and prevention of these attacks. The dataset undergoes pre-processing and is split into training and test datasets. Machine learning techniques are then utilized to predict and classify the attacks using the test dataset. The protocols which are examined during the attack are SNMP, NTP, UDP, and DNS. The accuracy is obtained by comparing the predicted results with the training dataset. Machine learning algorithms such as K- Nearest Neighbor(K-NN)-96.49%, Support Vector Machine (SVM)-79.61%, Random Forest (RF)-99.10%, and Gaussian Naïve Bayes (GNB)-78.75% have been found to produce high levels of accuracy for attack classification.
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.