Integrated Computer Network Security System: Intrusion Detection and Threat Prediction Using Machine Learning Algorithms

Mariya Utarbayeva, Makpal Mukanova

2024

Closed access Metadata (CSL-JSON)
DOI 10.1109/sist61555.2024.10629410
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The escalating use of computer networks and associated applications has made cybersecurity a critical concern. This research presents a comprehensive approach to addressing network security issues by developing an Intrusion Detection System (IDS) based on the dataset from the Security Information and Event Management System (SIEM) using various machine learning algorithms. The study includes a detailed comparison of models such as Logistic Regression, K-Nearest Neighbors, Gusain Naive Bayes, Support Vector Machine, Decision Tree, Random Forest, XGBoost, and Artificial Neural Networks. The results demonstrated using histograms and tables show the effectiveness of Random Forest and PCA Random Forest, emphasizing their accurate traffic classification. The research evaluates the model’s performance across various cyber-security datasets containing multiple categories of cyber-attacks. It evaluates efficiency by utilizing criteria such as accuracy, precision, and recall. By applying a multilevel approach aligned with the latest trends in machine learning, the study aims to facilitate swift and precise threat analysis and response, ultimately enhancing the overall effectiveness of the cybersecurity system. The study is an effective educational resource that introduces IT students to innovative machine learning and cybersecurity ideas. Through the integration of the results into IT curriculum, educators may close the knowledge gap between theory and practical application by offering students real-world experience in addressing cyber threats. This combined emphasis on innovation and education seeks to develop a new generation of IT professionals with the expertise required for enhanced cybersecurity.