<![CDATA[Abstract Distributed Denial of Service (DDoS) attacks are a serious threat to network security, aiming to disrupt services by overwhelming system resources with malicious traffic. The increasing complexity and variety of DDoS attack patterns demand the implementation of adaptive and accurate detection methods. This study examines the application of a Convolutional Neural Network (CNN) to classify DDoS attacks using the CICIoT 2023 dataset, which realistically represents Internet of Things (IoT) network traffic. The dataset underwent preprocessing stages including data cleaning, normalization, and splitting training and test data. A CNN model was designed to automatically extract features from network traffic data and classify between normal traffic and DDoS attacks. Test results show that the CNN model is capable of providing high levels of accuracy, precision, and recall, making it effective in detecting DDoS attacks in IoT environments. Thus, the CNN approach can be a reliable solution for enhancing deep learning-based intrusion detection systems in the face of dynamic DDoS threats. Keywords : Convolutional Neural Network, DDoS, Network Security, CICIoT 2023,Attack Classification.]]>
Copyrights © 2026
