Work

Analytics of Binary Class Detection & Forecasting of Cyber Incident by Machine Learning Methods

Year: 2024
Type: article
Abstract: In the rapidly evolving landscape of the digital era, the importance of cybersecurity has become paramount. As technology continues to advance, organizations and individuals are becoming increasingly interconnected, relying on digital platforms for communication, commerce, and critical infrastructure. This interconnectedness, while facilitating unprecedented convenience and efficiency, also exposes systems to a myriad of cybersecurity threats. This paper presents a proposed system designed to analyze network intrusion datasets. The dataset utilized comprises binary classified data, distinguishing between normal and attack types. We obtained the dataset from Kaggle for implementation purposes. Different machine learning methods, GNB, KNN, LR, SVM, DT, VC, RF, GB and XG are employed for the identification and categorization of cyber incident. A comparative analysis is conducted utilizing these machine learning algorithms. System performance is evaluated using Cross-Validation score, Recall value, F1 Score, Precision value and Accuracy value metrics. The analysis of system performance demonstrates which algorithm achieves the most accurate results.
Language: English
Open Access status: diamond
OpenAlex ID: W7217357829
FWCI: 0.321
Cites: 30
Cited by: 3
Related to: 10