On improving the performance of DDoS attack detection system

A DDoS (Distributed Denial of Service) attack is a harmful way of preventing regular access to a targeted machine, resources, or any network by flooding the target or its neighbouring infrastructure with massive traffic in an attempt to cause an interruption. As a result, the network environment's security has suffered significantly. Although numerous ways have been proposed in previous studies, there is still room for new ones as attacker patterns, and strategies change rapidly. This work designs a quick and efficient detection model to identify the latest real-world attacks. An attempt was made for an effective data pre-processing that includes both memory optimization and hybrid feature selection to improve the model's generalizability. Furthermore, the extreme learning machine (ELM) classifier is analyzed with the extracted features by varying weight ranges, hidden neurons, and activation functions to classify the attacks. Experiments are conducted using the CICDDoS-2019 traffic data. The experimental outcomes indicate that the suggested model is superior to previous strategies, with a detection accuracy of 99.94%.