Abstract

Distributed Denial-of-Service (DDoS) attacks are a major threat to the security and availability of online systems Organizations can use machine learning and deep learning to prevent distributed denial-of-service (DDoS) offensives. ML and DL can be used to identify and classify DDoS offensives, as well as to predict DDoS offensives. This can help organizations to take preventive measures before an offensive occurs. Random forests are a machine learning algorithm that has been shown to be effective for detecting and preventing DDoS attacks. This paper we use of random forests for DDoS prevention. We discuss the advantages and disadvantages of random forests for this task, and we present a case study of how random forests were used to detect and prevent a DDoS attack in a real world setting and conclude that random forests are a promising tool for DDoS prevention. They are robust to noise and outliers, and they have been shown to be effective in a variety of studies. However, more research is needed to develop and evaluate new random forest-based DDoS prevention techniques.