!Unmanned Aerial Vehicle (UAV or drone) classification is critical for surveillance, enabling the identification and distinction of drones for military, civilian, and other security applications. Although deep learning models trained on radio frequency (RF) signals show promise for drone classification, they often lack robustness in real-world and variable-noise environments. This limitation stems from their reliance on static feature fusion strategies, which cannot adaptively prioritize the most discriminative time-frequency information. To address this limitation, we propose a multi-scale convolutional neural network (MS-CNN) enhanced with a novel attention mechanism. Specifically, our model dynamically learns to weight multi-scale features extracted from Short-Time Fourier Transform (STFT) representations of RF signals, enabling it to focus on the most relevant signal characteristics under varying noise levels. Trained on a mixed signal-to-noise ratio (SNR) dataset augmented with synthetic additive white gaussian noise (AWGN), the MS-CNN learns inherent robustness without requiring explicit noise-specific tuning. When evaluated on the large-scale DroneRFa dataset, which comprises 24 drone classes and one noise class under controlled AWGN across an SNR range of -20 dB to 10 dB, our model achieves a peak accuracy of 99.04% at 0 dB SNR and consistently outperforms existing benchmark methods.

Abstract In modern embedded systems, security issues including side‐channel attacks (SCAs) are becoming of paramount importance since the embedded devices are ubiquitous in many categories of consumer electronics. Recently, deep learning (DL) has been introduced as a new promising approach for profiled and non‐profiled SCAs. This paper proposes and evaluates the applications of different DL techniques including the Convolutional Neural Network and the multilayer perceptron models for non‐profiled attacks on the AES‐128 encryption implementation. Especially, the proposed network is fine‐tuned with different number of hidden layers, labelling techniques and activation functions. Along with the designed models, a dataset reconstruction and labelling technique for the proposed model has also been performed for solving the high dimension data and imbalanced dataset problem. As a result, the DL based SCA with our reconstructed dataset for different targets of ASCAD, RISC‐V microcontroller, and ChipWhisperer boards has achieved a higher performance of non‐profiled attacks. Specifically, necessary investigations to evaluate the efficiency of the proposed techniques against different SCA countermeasures, such as masking and hiding, have been performed. In addition, the effect of the activation function on the proposed DL models was investigated. The experimental results have clarified that the exponential linear unit function is better than the rectified linear unit in fighting against noise generation‐based hiding countermeasure.

Unmanned aerial vehicle (UAV) contributes substantial strategic benefits on the Internet of Military Things (IoMT). However, the untrusted party’s misuse of the UAV may violate the security and even demolish the critical operation in the IoMT system. In addition, data manipulation and falsification using unauthorized access are the significant challenges of the IoMT system. In response to this problem, this study proposes a blockchain-integrated convolution neural network (CNN)-based intelligent framework named IoMT-Net for identification and tracking illegal UAV in the IoMT system. Blockchain technology prevents illicit access, data manipulation, and illegal intrusions, as well as stored data on the central control server (CCS). Concurrently, the proposed CNN analyzed the radio-frequency (RF) signal sent by the antenna array element to determine the Direction of Arrival (DoA) for the localization of the illegal UAV. Therefore, a signal model is designed to process the received signal array through IoMT-Net. Moreover, the proposed CNN model is designed with two different functional modules, such as the resource accuracy tradeoff (RAT) module and the unique feature extraction and accuracy boosting (UAB) module, by adopting depthwise and grouped convolution layers. These sparsely connected convolution layers offer high DoA estimation accuracy while maintaining the network more lightweight. In addition, the skip connection is also leveraged into the subunits of RAT and UAB modules for sharing features and handling the vanishing gradients problem. Based on the simulation results, the proposed network achieves superior DoA estimation accuracy (approximately 97.63% accuracy at 10-dB SNR) and outperforms other state-of-the-art models.

In oceanic remote sensing operations, underwater acoustic target recognition is always a difficult and extremely important task of sonar systems, especially in the condition of complex sound wave propagation characteristics. The expensively learning recognition model for big data analysis is typically an obstacle for most traditional machine learning (ML) algorithms, whereas the convolutional neural network (CNN), a type of deep neural network, can automatically extract features for accurate classification. In this study, we propose an approach using a dense CNN model for underwater target recognition. The network architecture is designed to cleverly reuse all former feature maps to optimize classification rates under various impaired conditions while satisfying low computational cost. In addition, instead of using time–frequency spectrogram images, the proposed scheme allows directly utilizing the original audio signal in the time domain as the network input data. Based on the experimental results evaluated on the real-world data set of passive sonar, our classification model achieves the overall accuracy of 98.85% at 0-dB signal-to-noise ratio (SNR) and outperforms traditional ML techniques, as well as other state-of-the-art CNN models.

Air pollution is a critical issue in cities in developing countries like Hanoi, Vietnam. An efficient and comprehensive air quality monitoring system may reduce the harmfulness and improve the cities' sustainability. This paper presents a novel approach to realize such a system in which the air monitoring sensors are mobile. More specifically, we introduce a three-tier architecture for the air quality system, including sensing, communication, and application layers. Initially, we discuss each layer concept to bypass the limitation of the traditional stationary monitoring system. We then describe our design and implementation of air quality monitoring devices installed on vehicles, such as buses. The device is carefully designed to satisfy the conditions of impedance matching and power integrity. Besides, it fully functions in measuring parameters from the ambient environment. The device is aware of its location (using GPS) and uses Wi-Fi and 4G (LTE) to transmit sensing data on the Internet. We have conducted various experiments, including a trial deployment of the devices on a vehicle running in Hanoi. The results show our device achieves sensing data transmission with high-reliability levels (i.e., 97%, 100% on Wi-Fi, 4G (LTE), respectively). Moreover, the trial deployment confirms the feasible operation of our device in actual condition.

This paper presents a deep learning-based method to automatically recognize low probability of intercept (LPI) radar waveforms against diversified jamming attacks. Concretely, an efficient convolutional neural network (CNN) architecture, namely Densely-Accumulated Network (DANet), is introduced to learn the time-frequency representation transformed by the Wigner-Ville distribution. Such an architecture has several novel densely-accumulated connection modules specified by various symmetric and asymmetric convolutional layers to enrich diversified features at multiple representational maps. Besides, the skip-connection and dense-connection are leveraged to improve feature learning efficiency and prevent the vanishing gradient when the network goes deeper. Some image processing techniques (e.g., global thresholding and digital filtering) are adopted to enhance the quality of time-frequency image. Relying on simulations, we benchmark the proposed method on a synthetic 13-waveform dataset and also investigate the influence of hyper-parameters (such as image size, number of modules, training data size) on the overall recognition performance. Remarkably, with average accuracy of 98.2% at 0 dB signal-to-noise ratio (SNR), DANet outperforms several backbone CNNs and state-of-the-art networks of LPI waveform recognition while keeping a cost-efficient model.

Modulation classification, recognized as the intermediate step between signal detection and demodulation, is widely deployed in several modern wireless communication systems. Although many approaches have been studied in the last decades for identifying the modulation format of an incoming signal, they often reveal the obstacle of learning radio characteristics for most traditional machine learning algorithms. To overcome this drawback, we propose an accurate modulation classification method by exploiting deep learning for being compatible with constellation diagram. Particularly, a convolutional neural network is developed for proficiently learning the most relevant radio characteristics of gray-scale constellation image. The deep network is specified by multiple processing blocks, where several grouped and asymmetric convolutional layers in each block are organized by a flow-in-flow structure for feature enrichment. These blocks are connected via skip-connection to prevent the vanishing gradient problem while effectively preserving the information identity throughout the network. Regarding several intensive simulations on the constellation image dataset of eight digital modulations, the proposed deep network achieves the remarkable classification accuracy of approximately 87% at 0 dB signal-to-noise ratio (SNR) under a multipath Rayleigh fading channel and further outperforms some state-of-the-art deep models of constellation-based modulation classification.

Modulation classification, an intermediate process between signal detection and demodulation in a physical layer, is now attracting more interest to the cognitive radio field, wherein the performance is powered by artificial intelligence algorithms. However, most existing conventional approaches pose the obstacle of effectively learning weakly discriminative modulation patterns. This paper proposes a robust modulation classification method by taking advantage of deep learning to capture the meaningful information of modulation signal at multi-scale feature representations. To this end, a novel architecture of convolutional neural network, namely Chain-Net, is developed with various asymmetric kernels organized in two processing flows and associated via depth-wise concatenation and element-wise addition for optimizing feature utilization. The network is evaluated on a big dataset of 14 challenging modulation formats, including analog and high-order digital techniques. The simulation results demonstrate that Chain-Net robustly classifies the modulation of radio signals suffering from a synthetic channel deterioration and further performs better than other deep networks.