Deep learning has become a research hotspot in the field of network intrusion detection. In order to further improve the detection accuracy and performance, we proposed an intrusion detection model based on improved deep belief network (DBN). Traditional neural network training methods, like Back Propagation (BP), start to train a model with preset parameters such as the randomly initialized weights and thresholds, which may bring some issues, e.g., attracting the model to the local optimal solutions, or requiring a long training period. We use the Kernel-based Extreme Learning Machine (KELM) with the supervised learning ability to replace the BP algorithm in DBN in a bid to ameliorate the situation. Considering the problem of poor classification performance usually caused by randomly initializing kernel parameters with KELM, an enhanced grey wolf optimizer (EGWO) is designed to optimize the parameters of KELM. In order to improve the search ability and optimization ability of the traditional grey wolf optimizer algorithm, a novel optimization strategy combining the inner and outer hunting is introduced. Experiments on KDDCup99, NSL-KDD, UNSW-NB15 and CICIDS2017 datasets show that the proposed DBN-EGWO-KELM algorithm has greater advantages in terms of its accuracy, precision, true positive rate, false positive rate and other evaluation indices compared with BP, RBF, SVM, KELM, LIBSVM, CNN, DBN-KELM and other intrusion detection models, and can effectively meet the requirements of intrusion detection of complex networks.

For the wireless sensor networks (WSNs) heterogeneous node deployment optimization problem with obstacles in the monitoring area, two new flower pollination algorithms (FPA) are proposed to deploy the network. Firstly, an improved flower pollination algorithm (IFPA) is proposed based on FPA, aiming at the shortcomings of the convergence speed is slow and the precision is not high enough of FPA. The nonlinear convergence factor is designed to correct the scaling factor of FPA, the Tent chaotic map effectively maintains the diversity of the population in the late iteration, and a greedy crossover strategy is designed to assist the remaining individual search with better individuals. Secondly, based on FPA, a non-dominated sorting multi-objective flower pollination algorithm (NSMOFPA) is proposed. The external archive strategy and leader strategy are introduced, to solve the global pollination problem. The proposed crowding degree method and the introduced elite strategy effectively maintain the diversity of the population. Then, IFPA is applied to WSN deployment aiming at optimizing coverage rate, simulation experiments show that IFPA can obtain a higher coverage rate with shorter iterations, which can save network deployment costs. Finally, applying NSMOFPA to the WSN deployment with optimization objectives for coverage rate, node radiation overflow rate and energy consumption rate. The experimental results verify that NSMOFPA has a good optimization effect and can provide a better solution for WSN deployment.

Aiming at the difficulty of deploying wireless sensor networks (WSNs) on three-dimensional (3D) surfaces, based on the grey wolf optimizer (GWO), an enhanced version of the grey wolf optimizer is proposed for deploying WSNs on 3D surfaces, namely the enhanced grey wolf optimizer (EGWO), which is characterized by enhanced exploitation and exploration ability of the algorithm. The novelty of EGWO is that the grey wolf population is divided into two parts, one part is responsible for the outer-layer encircle and the other is responsible for the inner-layer encircle, and the introduction of Tent mapping. The purpose of this is to enhance the exploitation and exploration ability of the algorithm respectively, so as to improve the convergence and optimization precision of the algorithm. In addition, in terms of WSN deployment in 3D surfaces, this paper improves the means of determining the perceived blind zone. Meanwhile, a novel method to calculate the WSNs coverage area of simple and complex 3D surfaces is presented by combining the grid and integral of the 3D surfaces. The EGWO is favorably compared with the GWO and three existing variants of the grey wolf optimizer when testing on 12 well-known benchmark functions. The simulation experiment results show that compared with the existing algorithms, EGWO can provide a very competitive search result in terms of optimization precision and convergence performance. Finally, this paper applies EGWO to the 3D surface deployment of WSN. Simulations show that compared with the other three deployment algorithms, EGWO can improve the network coverage of WSN, which can save network deployment costs. In addition, the probability of network connectivity deployed by EGWO is higher, that is, EGWO can provide a better deployment solution.

It is feasible and safe to use unmanned aerial vehicle (UAV) as the data collection platform of the Internet of things (IoT). In order to save the energy loss of the platform and make the UAV perform the collection work effectively, it is necessary to optimize the deployment of UAV. The objective problem is to minimize the sum of the lost energy of UAV and the loss of data transmission of Internet of things devices. The key to solving the problem is to calculate the location of the docking points and the number of docking points when the UAV is working to collect data. This paper proposes a coding scheme based on swarm intelligence optimization, which encapsulates the docking position of UAV into a dimension, so the number of docking points to be calculated is the dimension number of optimization objective. This problem is considered as a dynamic dimension optimization problem. Each individual in swarm intelligence algorithm is a solution. When adjusting the dimension, the best individual is added or deleted to achieve dynamic search in the evolutionary process. Collaborative search among multiple individuals can improve the local optimal limit of search to a certain extent. Finally, the validity of the swarm intelligence-based coding approach is verified by simulation experiments under seven different IoT device distribution scenarios.

The Internet of Things (IoT) environment contains many different types of devices, each with different functionalities, communication protocols, and security capabilities, which makes the IoT a complex challenge for security protection. Therefore, network intrusion detection (NID) is needed to detect intrusions in the network to secure the IoT. In recent years, deep learning-based intrusion detection systems have achieved excellent results, but they tend to require high computational resources and storage space, which is not feasible for most IoT devices. In this paper, we propose a lightweight intrusion detection model based on self-knowledge distillation, namely TBCLNN, which improves the detection accuracy while also reducing the number of model parameters and computational cost. Specifically, we use the binary Harris Hawk optimization algorithm for dimensionality reduction of traffic features. We use lightweight convolution, such as Tied Block Convolution (TBC), to design lightweight neural network models with residual and inverse residual structures. Moreover, we propose an improved self-knowledge distillation loss function to solve the sample imbalance problem and compensate for the performance degradation caused by lightweight neural networks. The multiclassification accuracy of our proposed method exceeds 99% on all three publicly available IoT datasets. The experimental results show that our method has a small model size and requires only low computational resources, making it suitable for resource-constrained IoT intrusion detection.

The combination of deep learning and intrusion detection has become a hot topic in today’s network security. In the face of massive, high-dimensional network traffic with uneven sample distribution, how to be able to accurately detect anomalous traffic is the primary task of intrusion detection. Most research on intrusion detection systems based on network anomalous traffic detection has focused on supervised learning; however, the process of obtaining labeled data often requires a lot of time and effort, as well as the support of network experts. Therefore, it is worthwhile investigating the development of label-free self-supervised learning-based approaches called BYOL which is a simple and elegant framework with sufficiently powerful feature extraction capabilities for intrusion detection systems. In this paper, we propose a new data augmentation strategy for intrusion detection data and an intrusion detection model based on label-free self-supervised learning, using a new data augmentation strategy to introduce a perturbation enhancement model to learn invariant feature representation capability and an improved BYOL self-supervised learning method to train the UNSW-NB15 intrusion detection dataset without labels to extract network traffic feature representations. Linear evaluation on UNSW-NB15 and transfer learning on NSK-KDD, KDD CUP99, CIC IDS2017, and CIDDS_001 achieve excellent performance in all metrics.