Intrusion detection is the core topic of network security, and the intrusion detection algorithm based on deep learning has become a research hotspot in network security. In this paper, a network intrusion detection classification model (NIDS-CNNLSTM) based on deep learning is constructed for the wireless sensing scenario of the Industrial Internet of Things (IIoT) to effectively distinguish and identify network traffic data and ensure the security of the equipment and operation of the IIoT. NIDS-CNNLSTM combines the powerful learning ability of long short-term memory neural networks in time series data, learns and classifies the features selected by the convolutional neural network, and verifies the applicability based on binary classification and multi-classification scenarios. The model is trained using KDD CUP99, NSL_KDD, and UNSW_NB15 classic datasets. The verification accuracy and training loss on the three datasets all show good convergence and level, and the accuracy rate is high when classifying various types of traffic. The overall performance of NIDS-CNNLSTM has been significantly improved compared with the models proposed in previous studies. The effectiveness shows a high detection rate and classification accuracy and a low false alarm rate through experimental results. It is more suitable for large-scale and multi-scenario network data in the IIoT.

With the rapid development of Industrial Internet of Things (IIoT), network security issues have become increasingly severe, making intrusion detection one of the key technologies for ensuring IIoT security. However, existing intrusion detection systems face challenges such as incomplete data features, missing labels, parameter leakage, and high communication overhead. To address these challenges, this paper proposes a federated learning-based intrusion detection algorithm (NIDS-FGPA) that utilizes gradient similarity model aggregation. This algorithm leverages a federated learning architecture and combines it with Paillier homomorphic encryption technology to ensure the security of the training process. Additionally, the paper introduces the Gradient Similarity Model Aggregation (GSA) algorithm, which dynamically selects and weights updates from different models to reduce communication overhead. Finally, the paper designs a deep learning model based on two-dimensional convolutional neural networks and bidirectional gated recurrent units (2DCNN-BIGRU) to handle incomplete data features and missing labels in network traffic data. Experimental validation on the Edge-IIoTset and CIC IoT 2023 datasets achieves accuracies of 94.5% and 99.2%, respectively. The results demonstrate that the NIDS-FGPA model possesses the ability to identify and capture complex network attacks, significantly enhancing the overall security of the network.

In city environment, the vehicle communication is affected by the around obstacles due to the especial condition of wireless channels. However, most of prior works adopt the fixed radio range value of vehicles to transmit packets. In this paper, we design an optimization forwarding range routing protocol for VANET in urban area. It has an optimized and adjustable forwarding range, which changes with different environments based on the path loss and the city model. And the proposed geo-routing protocol has a novel idea in computing the connectivity of roads and the adjustable strategy in a sparse network. Simulation results indicate that the OFRR enjoys desirable performance in the urban area.