A Review on Segmented Flood Attack Detection in Cloud Networks Using Machine Learning Methods
P. Dineshkumar, K. S. Geetha, R V Viswanathan, S. S. Sujatha, C. Rajan · 2024
Distributed Denial of Service (DDoS) attacks are one of the several issues disrupting the Internet at present. Cloud environments must have robust security mechanisms in place to ensure continuous service availability and lessen the impact of such attacks. The reason DDoS attacks are so difficult for Intrusion Detection Systems (IDS) is that they overwhelm system resources and complicate detection by flooding networks with malicious traffic. IDSs in the cloud use a variety of data mining and cyber analytics methods to detect and eliminate these threats. Numerous detection systems rely on machine learning algorithms, which have demonstrated potential in spotting malicious behavior and analyzing network patterns. With the help of the most recent datasets, this study seeks to improve detection skills by offering a thorough overview of the current DDoS threat landscape. Machine learning methods such as Random Forest and Gradient Boosting Machine (GBM) are used to categorize and forecast various DDoS attack types. To get into the study, a thorough method for anticipating and evaluating DDoS attacks was demonstrated. A comprehensive approach for predicting and analyzing DDoS attacks was examined to enter the research.