Contextual Internet of Things Intrusion Detection: A Sliding Window Convolutional Neural Network–Gated Recurrent Unit Model Enhanced by Graph Neural Networks

The rapid expansion of Internet of Things (IoT) devices has introduced significant security challenges, particularly in detecting sophisticated cyber intrusions. This study proposes a novel hybrid deep learning framework combining convolutional neural networks, gated recurrent units, and graph neural networks to enhance intrusion detection capabilities in IoT environments. The model effectively captures spatial features, temporal dependencies, and inter-device relationships within network traffic data. Evaluated on the ToN-IoT dataset, the proposed system achieved a high classification accuracy of 98%, with an area under the curve and average precision score of 1.00, along with strong precision, recall, and F1-scores across both normal and attack classes. These results were obtained using an 80:20 train-test split, demonstrating the model's robustness and suitability for real-time deployment in intelligent and dynamic IoT-based intrusion detection systems.