Improving Detection of Anomalies Associated with Distributed Denial -of-Service Attacks Using Artificial Intelligence and Supervised Machine Learning

Distributed Denial of Service (DDoS) attacks, due to their wide range and high destructive potential, pose a serious threat to cybersecurity. These attacks can lead to network slowdown and disruption in accessing software services and network resources. To address this issue, supervised machine learning models have been employed. In this study, various machine learning algorithms such as Random Forest and Logistic Regression were used to distinguish between normal and malicious traffic. The data was collected from the CSE-CICIDS۲۰۱۸ dataset and divided into training and testing sets. After feature scaling, the results indicated that the Random Forest model performed best with an accuracy of ۹۷.۶%, while the Logistic Regression model achieved an accuracy of ۹۱.۱%.

کلیدواژه ها:

Machine Learning ، Random Forest Algorithm ، Classification Algorithms ، Distributed Denial of Service (DDoS) Attacks