A Comparative Study of Machine Learning Models for Cyber-Attack Detection Emphasizing Performance and Legal Responsibility

Abstrak

The rapid growth of cyber threats and the increasing complexity of digital infrastructures have created an urgent need for intelligent and automated systems capable of identifying malicious activities within network environments. This study investigates the application of five machine learning algorithms, namely Logistic Regression, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and XGBoost, for the detection of cyber-attacks using a network traffic dataset.

Identifier

• OpenAlex: https://openalex.org/W7162402012
• DOI: https://doi.org/10.63913/jcl.v2i2.26