Machine Learning-Driven Detection of Malicious URLs and Network Intrusions

Document Type

Conference Proceeding

Source of Publication

2024 International Conference on Engineering and Emerging Technologies (ICEET)

Publication Date

12-28-2024

Abstract

The detection of malicious URLs and network intrusions is a critical task in cybersecurity. This study investigates the application of several machine learning models to classify network traffic data for intrusion detection purposes. The dataset, obtained, comprises 4,998 instances with 32 features related to network traffic attributes. Data preprocessing steps including normalization and feature selection based on information gain were applied. The study evaluates the performance of various classification algorithms, such as Support Vector Machines (SVM), AdaBoost, Random Forest, XGBoost, and Gaussian Naive Bayes. The XGBoost classifier achieves the highest accuracy of 92.1 %, demonstrating its effectiveness in detecting intrusions across several intrusion classes. The results highlight the potential of machine learning techniques in enhancing cybersecurity through malicious URLs and intrusion detection.

ISBN

979-8-3315-3289-5

Publisher

IEEE

Volume

00

First Page

1

Last Page

6

Disciplines

Computer Sciences

Keywords

Malicious URLs, Network Intrusions, Machine Learning, Intrusion Detection, Classification Algorithms

Indexed in Scopus

no

Open Access

no

Share

COinS