<![CDATA[The widespread adoption of electronic learning has made contemporary educational environments increasingly dependent on interconnected devices, enabling smart classrooms and remote monitoring systems. However, this technological advancement has also introduced substantial cybersecurity risks due to the vulnerabilities of unprotected, heterogeneous, and networked devices. Distributed Denial of Service (DDoS) attacks are among the most disruptive threats, as they can interrupt online classes, data access, and other educational services by flooding educational networks with illegitimate traffic. Existing signature-based DDoS detection mechanisms remain inadequate for Internet of Things (IoT) environments because of the dynamic nature of modern attacks and the resource limitations of connected devices. To address this challenge, this study proposed a hybrid deep learning model integrating Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) units, attention mechanisms, and incremental learning to enhance DDoS detection and prevention in Educational Internet of Things (EIoT) networks. The CNN layers were used to extract spatial features from network traffic, while the LSTM units captured temporal patterns and the attention mechanisms identified relevant traffic behavior. The incremental learning component employed geometric metrics to enable the model to capture previously unknown attack patterns. Experimental evaluation using the CIC-IoT2023 and BoT-IoT datasets showed that the proposed model achieved 99% detection accuracy for both known and emerging attacks in EIoT scenarios, supported by real-time traffic filtering and Software-Defined Networking (SDN)-based mitigation as prevention strategies. The model demonstrated strong adaptability, reduced false positives, and advanced AI-hybridized capabilities for DDoS detection and prevention in EIoT environments. These findings indicate that the proposed model is effective for detecting and preventing DDoS attacks against EIoT infrastructures and contributes to the development of adaptive cybersecurity solutions for technology-enhanced educational systems.]]>
Copyrights © 2026
