Automatic modulation classification (AMC) is becoming increasingly important for its fundamental role in dynamic spectrum access, which can support 5G wireless communications to refarm the spectrum resource with low utilization. In order to achieve a better classification performance, several AMC methods based on prototype and variant of convolutional neural networks (CNNs) have been proposed. However, most existing AMC methods based on CNNs only use monomodal information from either time domain or frequency domain. The complementary processing gain, which can be obatianed by fusing multimodal information from multiple transformation domain together, is neglected. To address the issue, we exploit a waveform-spectrum multimodal fusion (WSMF) method to realize AMC based on deep residual networks (Resnet). After extracting features from multimodal information using Resnet, we adopt a feature fusion strategy to merge multimodal features of signals to obtain more discriminating features. Simulation results demonstrate the superior performance of our proposed WSMF method compared with traditional CNNs based AMC method using single modality information. Our proposed method can distinguish among sixteen modulation signals, and it works well even for higher-order digital modulation types like 256QAM and 1024QAM.

In this letter, we consider the varying detection environments to address the problem of detecting small targets within sea clutter. We first extract three simple yet practically discriminative features from the returned signals in the time and frequency domains and then fuse them into a 3-D feature space. Based on the constructed space, we then adopt and elegantly modify the support vector machine to design a learning-based detector that enfolds the false alarm rate (FAR). Most importantly, our proposed detector can flexibly control the FAR by simply adjusting two introduced parameters, which facilitates to regulate detector's sensitivity to the outliers incurred by the sea spikes and to fairly evaluate the performance of different detection algorithms. Experimental results demonstrate that our proposed detector significantly improves the detection probability over several existing classical detectors in both low signal to clutter ratio (up to 58%) and low FAR (up to 40%) cases.

Automatic modulation classification (AMC) can generally be divided into knowledge-based methods and data-driven methods. In this paper, we explore combining the knowledge-based method and data-driven technology to take full advantage of both and propose a hybrid knowledge and data-driven deep learning framework (HKDD) for AMC. To make the handcrafted features more discriminative, various traditional features are adopted, including instantaneous features, statistical features, and spectral features. In the HKDD framework, a feature fusion mechanism is proposed to integrate the features learned from the original signal with those processed by a fully connected network from the handcrafted features. Besides, an attention mechanism is implemented on the fused features to neglect immature features and highlight important features. To evaluate the performance of the proposed method, we construct two modulation classification datasets containing both traditional features and raw IQ data. The bigger one contains 36 modulation categories, which is greater than the number of categories of any AMC dataset currently available. Simulation results show that our proposed method has significant performance gain in both adequate-sample classification scenario and few-shot classification scenario.

Benefit from the rapid evolution of artificial intelligence and wireless communication technology, diverse Internet of Things (IoT) devices with edge computing ability have widely penetrated every aspect of daily human life. However, the deviations of private datasets and the heterogeneity of local models caused by the difference in device composition and application scenarios have hampering the aggregation of global recognition model in modulation classification task, thus constraining the classification performance of intelligent IoT-edge devices severely. To address this problem, we propose a heterogenous Federated learning framework based on Bidirectional Knowledge Distillation (FedBKD) for IoT system, which integrates knowledge distillation into the local model upload (client-to-cloud) and global model download (cloud-to-client) steps of federated learning. The client-to-cloud distillation is regarded as a process of multi-teacher knowledge distillation and the global network is regarded as a student network that unifies the heterogeneous knowledge from multiple local teacher networks. A public dataset is generated by conditional variational autoencoder (CVAE) and stored in the cloud server for supporting the obtaining of heterogeneous knowledge without sharing the private data of IoT devices. The cloud-to-client distillation is single-teacher-multiple-students process, which distills the knowledge from the single global model back to multiple heterogeneous local networks and partial knowledge distillation is used in this process. We implement our FedBKD method in the modulation classification task and the simulation results have proven the effectiveness of our proposed method.

Advances in adversarial attack and defense technologies will enhance the reliability of deep learning (DL) systems spirally. Most existing adversarial attack methods make overly ideal assumptions, which creates the illusion that the DL system can be attacked simply and has restricted the further improvement on DL systems. To perform practical adversarial attacks, a detection tolerant black-box adversarial-attack (DTBA) method against DL-based automatic modulation classification (AMC) is presented in this article. In the DTBA method, the local DL model as a substitution of the remote target DL model is trained first. The training dataset is generated by an attacker, labeled by the target model, and augmented by Jacobian transformation. Then, the conventional gradient attack method is utilized to generate adversarial attack examples toward the local DL model. Moreover, before launching attack to the target model, the local model estimates the misclassification probability of the perturbed examples in advance and deletes those invalid adversarial examples. Compared with related attack methods of different criteria on public datasets, the DTBA method can reduce the attack cost while increasing the rate of successful attack. Adversarial attack transferability of the proposed method on the target model has increased by more than 20%. The DTBA method will be suitable for launching flexible and effective black-box adversarial attacks against DL-based AMC systems.

In this paper, we propose a covert wireless uplink transmission strategy in space-air-ground integrated vehicular networks, where the source vehicle transmits its own message over the channel that being used by the host communication system, to avoid being detected by the warden. It is obvious that the data transmission efficiency of the covert communication system is limited due to the co-channel interference. To improve the data transmission efficiency, we consider that the covert communication system adopts improper Gaussian signaling (IGS). We formulate a joint transmit power and IGS factor optimization problem to minimize the outage probability of the covert communication system. The minimum error detection probability of the warden is first analyzed with noise uncertainty, which is used to measure the system covertness. Under the constraints of the quality of service (QoS) of host communication system and the covertness requirement, the optimal transmit power is first derived with proper Gaussian signaling (PGS) scheme. Then, with the approximate outage probability derived under IGS scheme, the optimization problem is solved by jointly designing the transmit power and IGS factor. Finally, we provide extensive numerical results to validate the proposed covert transmission strategy, and demonstrate that the IGS scheme is beneficial in improving the data transmission efficiency in terms of outage probability compared to PGS scheme.