ISBN: 9786630189629 - a hybrid ensemble machine learning model for cyber threat detection (3 resultados)

Taschenbuch. Condición: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware 216 pp. Englisch.

Taschenbuch. Condición: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - The rapid growth of digital technologies and internet-based services has significantly increased cybersecurity risks, necessitating more effective and intelligent threat detection mechanisms. Traditional cybersecurity approaches, including signature-based and behavior-based detection techniques, often struggle to cope with the increasing complexity and diversity of modern cyberattacks. To address these limitations, this study proposes a hybrid machine learning framework for cyber threat detection and classification that combines the strengths of multiple learning algorithms through a weighted voting strategy. The proposed framework integrates six machine learning classifiers: K-Nearest Neighbors (KNN), Random Forest (RF), Naïve Bayes (NB), Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and Light Gradient Boosting (LGB). An empirical evaluation was conducted to assess their performance in both binary and multiclass classification tasks. For binary classification, the individual models achieved accuracies of 91.78% (KNN), 94.29% (RF), 82.18% (NB), 90.70% (SVM), 87.39% (LDA), and 94.24% (LGB).…

Taschenbuch. Condición: Neu. This item is printed on demand - Print on Demand Titel. Neuware -The rapid growth of digital technologies and internet-based services has significantly increased cybersecurity risks, necessitating more effective and intelligent threat detection mechanisms. Traditional cybersecurity approaches, including signature-based and behavior-based detection techniques, often struggle to cope with the increasing complexity and diversity of modern cyberattacks. To address these limitations, this study proposes a hybrid machine learning framework for cyber threat detection and classification that combines the strengths of multiple learning algorithms through a weighted voting strategy. The proposed framework integrates six machine learning classifiers: K-Nearest Neighbors (KNN), Random Forest (RF), Naïve Bayes (NB), Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and Light Gradient Boosting (LGB). An empirical evaluation was conducted to assess their performance in both binary and multiclass classification tasks. For binary classification, the individual models achieved accuracies of 91.78% (KNN), 94.29% (RF), 82.18% (NB), 90.70% (SVM), 87.39% (LDA), and 94.24% (LGB). 216 pp. Englisch.…