<![CDATA[The increasing reliance on digital network infrastructures in higher education institutions has significantly increased the exposure of campus networks to various cyber threats. Cyberattacks such as distributed denial-of-service (DDoS), malware infections, and unauthorized access attempts can disrupt academic services and compromise sensitive institutional data. Therefore, developing an effective intrusion detection mechanism is essential to enhance cybersecurity within campus network environments. This study proposes a machine learning framework for cyberattack detection in campus networks by analyzing network traffic patterns using supervised machine learning algorithms. The proposed framework consists of several stages including dataset acquisition, data preprocessing, feature selection, model training, and performance evaluation. Experiments were conducted using the CICIDS2017 dataset, which contains both benign network traffic and multiple types of cyberattack scenarios. Three machine learning models, namely Random Forest, Support Vector Machine (SVM), and XGBoost, were implemented and compared in order to evaluate their effectiveness in detecting malicious network activities. The experimental results indicate that the XGBoost model achieved the highest performance, with an accuracy of 95.3%, outperforming the other evaluated models. These findings demonstrate that machine learning techniques can effectively identify abnormal network traffic patterns and improve cyberattack detection capabilities. The proposed framework provides a promising approach for strengthening cybersecurity monitoring and enhancing the resilience of campus network infrastructures against evolving cyber threats.]]>
Copyrights © 2025
