<![CDATA[The implementation of Internet of Things (IoT) systems and applications is increasingly widespread across various fields. This makes IoT an attractive target for cyber crime, especially Distributed Denial of Service (DDoS) attacks such as SYN Flood. This type of attack disrupts service availability and floods servers, causing them to lose resources. One method for detecting DDoS attacks is through an Intrusion Detection System (IDS). A novel technique in IDS implementation is Deep Learning, specifically the Deep Neural Network (DNN) method, capable of identifying precise mathematical manipulations to transform input into output. Therefore, this research proposes the use of the DNN method to detect SYN Flood DDoS attacks in IoT networks. Testing results from the study, which utilized the CICIoT2023 dataset consisting of 14 files with two labels, DDoS-SYN_Flood and BenignTraffic, provided satisfactory outcomes. Evaluation using epochs with values of 10, 50, and 100 showed that epoch 100 yielded the highest performance. This is evident from the average accuracy rate of 99.36%, precision of 99.44%, recall of 99.75%, and an f1-score of 99.59%.]]>
Copyrights © 2024
