<![CDATA[With the rapid expansion of IoT (Internet of Things) devices, ensuring network security has become a critical challenge. Distributed Denial of Service (DoS) and spoofing attacks are among the most common and damaging threats in IoT ecosystems. Traditional Intrusion Detection Systems (IDS) often face difficulties in detecting these attacks due to the high volume and complexity of IoT network traffic. This study introduces a novel Deep Neural Network (DNN)-based IDS designed to effectively detect DoS and spoofing attacks using the CICIoT 2024 dataset. The CICIoT 2024 dataset provides a comprehensive benchmark with realistic IoT network traffic patterns, including benign and malicious activities. The results highlight the potential of DDN-based IDS to enhance IoT network security, paving the way for more resilient and intelligent defense mechanisms against evolving cyber threats. The detection results are promising, significantly improving attack detection performance, reaching up to 100%.]]>
Copyrights © 2025
