Detection of Distributed Denial of Service Attacks in the Cloud Using Machine Learning Method

Cyber-attack classification using deep learning and machine learning models is very suitable for classifying digital threats based on their characteristics and behaviors because these models examine system logs, network traffic, or other relevant data patterns to distinguish between standard activities and malicious actions. The main challenge in developing a machine learning-based intrusion detection system is the lack of large and labeled datasets. Using suitable features to train the algorithms is also critical. In this paper, we benefited from the Salp Swarm Optimization algorithm as a method to select important features. Then, a support vector machine is used to classify network traffic as either normal or abnormal. We compared the proposed method to state-of-the-art approaches on the BUETDDoS2020, Bot-IoT, and CICDDOS datasets. Results show that the suggested approach leads to a high true positive rate, a low false positive rate, and scores close to one in terms of precision, recall, and F-measure.