Statistical and density-based clustering techniques in the context of anomaly detection in network systems: A comparative analysis

In the modern world, the volume of data stored electronically and transmitted over networks continues to grow rapidly. This trend increases the demand for the development of effective methods to protect information transmitted over networks as network traffic. Anomaly detection plays a crucial role in ensuring net security and safeguarding data against cyberattacks. This study aims to review statistical and density-based clustering methods used for anomaly detection in network systems and to perform a comparative analysis based on a specific task. To achieve this goal, the authors analyzed existing approaches to anomaly detection using clustering methods. Various algorithms and clustering techniques applied within network environments were examined in this study. The comparative analysis highlights the high effectiveness of clustering methods in detecting anomalies in network traffic. These findings support the recommendation to integrate such methods into intrusion detection systems to enhance information security levels. The study identified common features, differences, strengths, and limitations of the different methods. The results offer practical insights for improving intrusion detection systems and strengthening data protection in network infrastructures.