The Internet of Things (IoT) is widely applied in modern human life, e.g., smart home and intelligent transportation. However, it is vulnerable to malicious attacks, and the current existing security mechanisms cannot completely protect the IoT. As a security technology, intrusion detection can defend IoT devices from most malicious attacks. However, unfortunately the traditional intrusion detection models have defects in terms of time efficiency and detection efficiency. Therefore, in this paper, we propose an improved linear discriminant analysis (LDA)-based extreme learning machine (ELM) classification for the intrusion detection algorithm (ILECA). First, we improve the linear discriminant analysis (LDA) and then use it to reduce the feature dimensions. Moreover, we use a single hidden layer neural network extreme learning machine (ELM) algorithm to classify the dimensionality-reduced data. Considering the high requirement of IoT devices for detection efficiency, our scheme not only ensures the accuracy of intrusion detection, but also improves the execution efficiency, which can quickly identify the intrusion. Finally, we conduct experiments on the NSL-KDD dataset. The evaluation results show that the proposed ILECA has good generalization and real-time characteristics, and the detection accuracy is up to 92.35%, which is better than other typical algorithms.

Automatic modulation classification (AMC) is an important technology for the monitoring, management, and control of communication systems. In recent years, machine learning approaches are becoming popular to improve the effectiveness of AMC for radio signals. However, the automatic modulation open-set recognition (AMOSR) scheme that aims to identify the known modulation types and recognize the unknown modulation signals is not well studied. Therefore, in this paper, we propose a novel multi-modal marginal prototype framework for radio frequency (RF) signals ( MMPRF ) to improve AMOSR performance. First, MMPRF addresses the problem of simultaneous recognition of closed and open sets by partitioning the feature space in the way of one versus other and marginal restrictions. Second, we exploit the wireless signal domain knowledge to extract a series of signal-related features to enhance the AMOSR capability. In addition, we propose a GAN-based unknown sample generation strategy to allow the model to understand the unknown world. Finally, we conduct extensive experiments on several publicly available radio modulation data, and experimental results show that our proposed MMPRF outperforms the state-of-the-art AMOSR methods.

As part of the IoT-based application, underwater wireless sensor networks (UWSN), which are typically self-organized heterogeneous wireless network, are one of the research hot-spots using various sensors in marine exploration and water environment monitoring application fields, recently. Due to the serious attenuation of radio in water, acoustic or hybrid communication is a usual way for transmitting information among nodes, which dissipates much more energy to prevent the network failure and guarantee the quality of service (QoS). To address this issue, a topology control with energy balance, namely TCEB, is proposed for UWSN to overcome time-delay and other interference, as well as make the entire network load balance. With the given underwater network model and its specialized energy consumption model, we introduce the non-cooperative-game-based scheme to select the nodes with better performance as the cluster-heads. Afterwards, the intra-cluster and inter-cluster topology construction are, respectively, to form the effective communication links of the intra-cluster and inter-cluster, which aim to build energy-efficient topology to reduce energy consumption. With the demonstration of the simulation, the results show the proposed TCEB has better performance on energy-efficiency and throughput than three other representative algorithms in complex underwater environments.

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing, and memory. Discovering the specialized CNN that meets a specific constraint requires a substantial effort of human experts. Compared with hand-designed approaches, neural architecture search (NAS) appears as a practical technique in automating the manual architecture design process and has attracted increasing interest in spoken language processing tasks such as speaker recognition. In this paper, we propose EfficientTDNN, an efficient architecture search framework consisting of a TDNN-based supernet and a TDNN-NAS algorithm. The proposed supernet introduces temporal convolution of different ranges of the receptive field and feature aggregation of various resolutions from different layers to TDNN. On top of it, the TDNN-NAS algorithm quickly searches for the desired TDNN architecture via weight-sharing subnets, which surprisingly reduces computation while handling the vast number of devices with various resources requirements. Experimental results on the VoxCeleb dataset show the proposed EfficientTDNN enables approximate $10^{13}$ architectures concerning depth, kernel, and width. Considering different computation constraints, it achieves a 2.20% equal error rate (EER) with 204 M multiply-accumulate operations (MACs), 1.41% EER with 571 M MACs as well as 0.94% EER with 1.45 G MACs. Comprehensive investigations suggest that the trained supernet generalizes subnets not sampled during training and obtains a favorable trade-off between accuracy and efficiency.

Cyber-physical systems (CPS) have been deployed in many areas and have reached unprecedented levels of performance and efficiency. However, the security and privacy problems in CPS have not been properly addressed, e.g., the monitored source location can be inferred by an attacker, which can substantially undermine the reliability of CPS. Unfortunately, the existing techniques to protect against the leakage of the source location do not achieve an acceptable balance among the source location privacy, transmission delay, and energy consumption to guarantee high reliability. To address this issue, we propose an attacker location evaluation-based fake source scheduling (FSSE) for source location privacy in CPS to enhance the privacy level and maintain the system performance. The proposed FSSE contains two main phases. The first, backbone construction, is dependent on the probability of capture derived from the communication information of self and neighboring nodes. This phase aims to build a backbone to form a baseline with respect to the source location privacy and transmission delay. The second phase is fake message scheduling, which is established to provide a trade-off among privacy, transmission delay, and communication overhead in terms of the hypothesized location of the attacker by using stochastic processes. Through analysis and simulation, we demonstrate that the proposed method has a more stable privacy level and more efficient transmission delay and energy consumption than the three compared algorithms, i.e., phantom routing, tree-based diversionary routing, and dynamic fake source selection.