Modulation Classification of Active Attacks in Internet of Things: Lightweight MCBLDN With Spatial Transformer Network

This article focuses on automatic modulation classification (AMC) in wireless communication systems. A convolutional neural network (CNN) with three layers is introduced for the AMC process. Over degraded channels, it is assumed that the constellation diagrams of received signals do not show sharp points as in the case of pure signals. Instead, the points spread to constitute circle‐shaped objects. With more deterioration in channel conditions, these circle‐shaped objects begin to show overlapping. This behavior motivates us to use object detection, when dealing with the modulation classification task. The selection of the adopted transforms in this article is made from the object detection perspective. Different 2D transforms are considered on the constellation diagrams and compared for better classification performance. These transforms are the Radon transform (RT), the curvelet transform, and the phase congruency (PC). They are applied on the 2D constellation diagrams prior to the classification task with the CNN. The classification of the modulation format at different signal‐to‐noise ratios (SNRs) is considered in this article from the constellation diagrams, and the preprocessed constellation diagrams using RT, curvelet transform, and PC. Seven types of modulation formats are considered in this study to represent both spread and dense constellation diagram patterns, and the study extends from −10 to 10 dB. Analysis of the results indicating the most suitable preprocessor according to the constellation type and the SNR involved is provided.

The development of the Internet-of-Things (IoT) security is comparatively slower than the pace of the IoT innovations. The seamless IoT network operates in an untrusted environment and is exposed to many malicious active attacks. As the process of identifying the modulation format of signals is corrupted by noise and fading, automatic modulation classification (AMC) can be viewed as an effective approach to counter physical-layer threats for IoT as it can detect and identify the pilot jamming, deceptive jamming, and Sybil attacks. Nowadays, data-driven deep learning (DL) techniques, which are capable of extracting discriminative features and perform better robustness to channel and noise conditions, have drawn widespread attention. The deep residual network (ResNet) has a strong representative ability, which can learn latent information repeatedly from the received signals and improve the classification accuracy. Meanwhile, the gated recurrent unit (GRU), which is capable of exploiting temporal information of the received signal can expand the dimension of the signal features for satisfactory classification performance. Considering the advantages of the above networks, this article proposes a novel gated recurrent residual neural network (GrrNet) for feature-based AMC, where the amplitude and phase of the received signal are utilized as the inputs of GrrNet. In GrrNet, a ResNet extractor module is first designed to extract the highly representative features and then temporal information is obtained by the subsequent GRU module which is capable of processing the representative features with the arbitrary length for modulation classification. Moreover, extensive simulations are conducted to verify the classification performance and robustness of the proposed GrrNet and it is shown that GrrNet outperforms other recent DL-based AMC methods. Moreover, the influence of the network parameters, symbol length, and frequency offset on performance is also explored.

Internet of Things (IoT) networks are often subject to many malicious attacks in untrusted environments, and automatic modulation classification (AMC) is an effective way to combat IoT physical-layer threats. However, most existing AMC methods assume sufficient labeled signals and invariant signal distribution, which is often impossible in untrusted environments. In this article, a new meta-learning method is proposed for a few-shot AMC with distribution bias. First, a multi-frequency octave ResNet (MFOR) is constructed to learn coarse (low-frequency) and fine (high-frequency) features, which can efficiently identify the modulation type of the signal while saving computational resources. Second, a large number of classification-related meta-tasks are established for training MFOR to explore general knowledge in signal classification, and then transfer it to the AMC. Different with deep neural networks (DNNs) that learn a mapping by multiple instances, the MFOR with meta-learning (denoted as M-MFOR) can improve the generalization ability of new AMC tasks with very few instances and distribution bias. Furthermore, we find that the distribution bias between data can be reduced by adjusting the normalized distribution and propose a class-related mixup. Extensive experiments are taken on several datasets to investigate the effectiveness of M-MFOR. The results show its feasibility and superiority over existing methods.

Automatic modulation classification (AMC) is to identify the modulation type of a received signal, which plays a vital role to ensure the physical-layer security for Internet of Things (IoT) networks. Inspired by the great success of deep learning in pattern recognition, the convolutional neural network (CNN) and recurrent neural network (RNN) are introduced into the AMC. In general, there are two popular data formats used by AMC, which are the in-phase/quadrature (I/Q) representation and amplitude/phase (A/P) representation, respectively. However, most of AMC algorithms aim at structure innovations, while the differences and characteristics of I/Q and A/P are ignored to analyze. In this article, lots of popular AMC algorithms are reproduced and evaluated on the same data set, where the I/Q and A/P are used, respectively, for comparison. Based on the experimental results, it is found that: 1) CNN-RNN-like algorithms using A/P as input data are superior to those using I/Q at high signal-to-noise ratio (SNR), while it has an opposite result in low SNR and 2) the features extracted from I/Q and A/P are complementary to each other. Motivated by the aforementioned findings, a multitask learning-based deep neural network (MLDNN) is proposed, which effectively fuses I/Q and A/P. In addition, the MLDNN also has a novel backbone, which is made up of three blocks to extract discriminative features, and they are CNN block, bidirectional gated recurrent unit (BiGRU) block, and a step attention fusion network (SAFN) block. Different from most of CNN-RNN-like algorithms (i.e., they only use the last step outputs of RNN), all step outputs of BiGRU can be effectively utilized by MLDNN with the help of SAFN. Extensive simulations are conducted to verify that the proposed MLDNN achieves superior performance in the public benchmark.

This chapter emphasizes the attributes of typical Internet of Things (IoT) systems and presents the most significant security risks that such systems may be subjected to in their operation. A lot of research efforts have been devoted to studying and categorizing IoT vulnerabilities and attacks. Given the attacker's activity as a categorization criterion, IoT attacks can be broadly classified as passive and active attacks. IoT risks or malicious behaviors can be detected early on in the IoT system's lifecycle by aggregating and analyzing data provided by various IoT sectors, which can then be studied by one or some artificial intelligence (AI) approaches to distinguish regular behaviors from malicious behaviors. Machine learning (ML) is regarded as a widely applied AI paradigm. Deep learning is an ML technology that creates deeper versions of neural networks that imitate the composition and functionality of the human brain.

Spatial transformer networks (STNs) were designed to enable convolutional neural networks (CNNs) to learn invariance to image transformations. STNs were originally proposed to transform CNN feature maps as well as input images. This enables the use of more complex features when predicting transformation parameters. However, since STNs perform a purely spatial transformation, they do not, in the general case, have the ability to align the feature maps of a transformed image with those of its original. STNs are therefore unable to support invariance when transforming CNN feature maps. We present a simple proof for this and study the practical implications, showing that this inability is coupled with decreased classification accuracy. We therefore investigate alternative STN architectures that make use of complex features. We find that while deeper localization networks are difficult to train, localization networks that share parameters with the classification network remain stable as they grow deeper, which allows for higher classification accuracy on difficult datasets. Finally, we explore the interaction between localization network complexity and iterative image alignment.

Convolutional Neural Networks (CNN) have achieved great performance in many visual tasks. However, CNN models are sensitive to samples with large spatial variants, especially severe in fine-grained classification task. In this paper, we propose a novel CNN model called ST-BCNN to solve these problems. ST-BCNN contains two functional CNN modules: Spatial Transform Network (STN) and Bilinear CNN(BCNN). Firstly, STN module is used to select key region in input samples and get it spatially modified. Since the adoption of STN will cause an information loss phenomenon called boundary loss, we design a brand-new IOU loss method to solve it. We make a theoretical analysis of the IOU loss method. Secondly, to discover discriminative features for fine-grained classification task, BCNN module is applied. BCNN interacts CNN features from different channels to produce more discriminative bilinear features than fully connected features of CNN. ST-BCNN works by reducing irrelevant spatial states and producing fine-grained features. We evaluate our model on 3 public fine-grained classification datasets with large spatial variants: CUB200-2011, Fish100 and UAV43. Experiments show that the IOU loss method can reduce boundary loss and make STN module output spatial transformed image appropriately. Our proposed ST-BCNN model outperforms other advanced CNN models on all three datasets.

Automatic modulation classification (AMC) plays an important role in many fields to identify the modulation type of wireless signals. In this paper, we introduce deep learning to signal recognition. Based on architecture analysis of the convolutional neural network (CNN), we used real signal data generated by instruments as dataset, and proposed an improved CNN architecture to achieve compatible recognition accuracy of modulation classification. According to various conditions of signal noise ratio (SNR), we test the proposed CNN architecture with the real sampled signals. Experiments results show that the high-layer network is not necessary for modulation recognition with high SNR signals. The proposed CNN architecture has higher average classification accuracy than RESNET and is more compatible for modulation classification of signals with lower SNR.

The Automatic Modulation Classification (AMC) of the underwater acoustic communication signals is still difficult via traditional methods in the case of poor underwater acoustic channels condition and impulse noise. In this paper, we propose a novel deep neural network model for AMC of underwater acoustic communication combining the convolutional neural network (CNN) and the long short-term memory network (LSTM). The CNN learns from time domain IQ data and LSTM learns from amplitude and phase. Multipath fading underwater acoustic channels with alpha-stable impulse noise and doppler frequency shift are modeled for signal dataset generation based on the real marine environment data. Experimental results validate this approach has a high recognition rate with the burst low SNR signal and has a performance stability under the Alpha-stable impulse noise, which is better compared to other existing schemes.

Automatic modulation classification using KELM with joint features of CNN and LBP

Cognitive Radio (CR) systems allow optimizing the use of the shared radio spectrum and enhancing the coexistence among different technologies by efficiently changing certain operating parameters of the radios such as transmit-power, carrier frequency, and modulation and coding scheme in real-time. Dynamic Spectrum Access (DSA), which allows radios to dynamically access and use the unused spectrum, is one of the tasks that are fundamental for a better use of the spectrum. In this paper, we extend the previous work on Automatic Modulation Classification (AMC) by using Deep Neural Network (DNNs) and evaluate the performance of these architectures on signals that are not only modulated but are also encoded. We call this the Automatic Modulation and Coding Scheme Classification problem, or \(AMC^2\). In this problem, radio signals are classified according to the Modulation and Coding Scheme (MCS) used during their transmission. Evaluations on a data set of 802.11 radio signals, transmitted with different MCS and Signal to Noise Ratio (SNR), provide important results on the impact of some DNN hyperparameters, e.g. number of layers, batch size, etc., in the classification accuracy.

Artificial intelligence (AI) relies on pattern recognition and classification algorithms to achieve accurate and efficient decision-making. Convolutional neural networks (CNNs) are the state-of-the-art for processing 2D image data, but their high computational and data requirements limit their use in resource-constrained environments. Hyperdimensional computing (HDC) offers a lightweight alternative, excelling in 1D tasks, but struggles to achieve competitive accuracy for 2D image classification. Hybrid frameworks combining HDC with CNNs have been proposed to improve accuracy but inherit the computational demands of deep learning, making them unsuitable for edge and IoT devices. To address this, we propose TransHD, a framework integrating lightweight spatial transformer networks (STNs) with HDC to enhance image classification performance while maintaining efficiency. TransHD achieves up to 9% higher accuracy than base HDC models on MNIST and Fashion-MNIST using only 30% of the training data, and reduces computational complexity by 2.5x through optimized STN feature map usage. On resource-constrained platforms like the Raspberry Pi 4, TransHD accelerates inference times by 3.4x and improves energy efficiency by 3.2x, with an accuracy trade-off of approximately 3% compared to CNNs. This study demonstrates the potential of combining HDC with STNs to develop efficient AI solutions for IoT and edge computing, where low energy consumption and computational efficiency are critical.

Security issue in Internet of Things (IoT) is one of the most important aspects to be resolved. Some attacks that occurred in Internet technology are also penetrated IoT. A trust-based security system is a promising solution in IoT as it is suitable for the characteristic of IoT which is distributed, decentralized control and on-off connections. Knowing the behaviors of the attacks might help up to understand of how we may prevent the attacks and plan to mitigate the attacks. In this paper, we simulated trust-based attacks in IoT environment by giving the fake reputation values of an object. For this purpose, we utilized ConTrust model, a trust-based security model. Matlab was used to simulate the attacks, and the simulation result showed that ConTrust model was outperformed on mitigating a trust-based attack. The attack was detected and resolved correctly.

Real-time modulation classification architecture in software defined radio

Hyperspectral image (HSI) classification is fundamental to a wide range of remote sensing applications, such as precision agriculture, environmental monitoring, and urban planning, because HSIs provide rich spectral signatures that enable the discrimination of subtle material differences. Deep learning approaches, including Convolutional Neural Networks (CNNs), Graph Convolutional Networks (GCNs), and Transformers, have achieved strong performance in learning spatial–spectral representations. However, these models often face difficulties in jointly modeling long-range dependencies, fine-grained local structures, and non-Euclidean spatial relationships, particularly when labeled training data are scarce. This paper proposes a Spectral–Spatial Graph Transformer Network (SSGTN), a dual-branch architecture that integrates superpixel-based graph modeling with Transformer-based global reasoning. SSGTN consists of four key components, namely (1) an LDA-SLIC superpixel graph construction module that preserves discriminative spectral–spatial structures while reducing computational complexity, (2) a lightweight spectral denoising module based on 1×1 convolutions and batch normalization to suppress redundant and noisy bands, (3) a Spectral–Spatial Shift Module (SSSM) that enables efficient multi-scale feature fusion through channel-wise and spatial-wise shift operations, and (4) a dual-branch GCN-Transformer block that jointly models local graph topology and global spectral–spatial dependencies. Extensive experiments on three public HSI datasets (Indian Pines, WHU-Hi-LongKou, and Houston2018) under limited supervision (1% training samples) demonstrate that SSGTN consistently outperforms state-of-the-art CNN-, Transformer-, Mamba-, and GCN-based methods in overall accuracy, Average Accuracy, and the κ coefficient. The proposed framework provides an effective baseline for HSI classification under limited supervision and highlights the benefits of integrating graph-based structural priors with global contextual modeling.