In regards to electromagnetic warfare application, this work proposes a radar intra-pulse recognition algorithm based on bicubic interpolation Wigner-Ville distribution (WVD). The proposed method is aimed at overcoming the complexity of traditional feature extraction and enhancing the robustness of intelligent intra-pulse recognition systems. Firstly, we convert the WVD matrices of radar intra-pulse signals into square matrices using bicubic interpolation. This enables the intra-pulse recognition algorithm to handle radar signals with varying lengths. Secondly, we use the square matrices directly to train a convolutional neural network (CNN), rather than first saving them as images and then training the network with those images. This is because automatic storage and retrieval of images can sometimes alter the numerical values in the matrices. We enhance the performance of the CNN by utilizing batch normalization and one-hot encoding techniques, and continuously evaluate the CNN during training to save the best performing model. Finally, we use the trained CNN to identify the intercepted radar intra-pulses, and verify the reliability of the proposed method based on radar signals generated by hardware devices. Experimental results demonstrate that the proposed algorithm can recognize radar intra-pulses with varying pulse widths. Furthermore, the proposed algorithm exhibits strong recognition performance even at low signal-to-noise ratio, and has lower time complexity than existing algorithms.

It is difficult to recognize Automatic Link Establishment (ALE) behaviors of a short-wave radio station, if we do not acquire the radio station’s communication protocol standard. A method is proposed to recognize different ALE behaviors by using an improved unidimensional DenseNet. In this work, we directly recognize ALE signals in physical layer without the radio station’s communication protocol standard. Hence, we can avoid difficulties in demodulation, decryption and so on. Actually, the original DenseNet is used extensively in the field of computer vision, so the original DenseNet is firstly adapted for the unidimensional input. And then, two parallel dense blocks are used in our improved unidimensional DenseNet, which could improve the capability of network to extract ALE signals’ deep features. The experimental results show that the proposed method is able to recognize different ALE behaviors of a short-wave radio station. And improved DenseNet has better recognition performance than simple DenseNet. The simple DenseNet only contains one dense block. Finally, the results of comparison experiments also show that some classic networks have worse performance in ALE behaviors recognition, such as LeNet-5, ResNet-34, and DenseNet-121.

Specific emitter identification involves extracting the fingerprint features that represent the individual differences of the emitter through processing the received signals. By identifying the extracted fingerprint features, one can also identify the emitter to which the received signals belong. Due to differences in transmitter hardware, this fingerprint cannot be duplicated. Therefore, SEI plays an important role in the field of information security and can reduce the information leakages caused by key theft. This method can also be used in the military field to support communication countermeasures via emitter individual identification. In this paper, empirical mode decomposition is carried out for each radar pulse signal, and then the bispectral features are extracted. Dimensionality reduction is carried out according to the symmetry of the bispectral features. The features after dimensionality reduction are input into a one-dimensional LeNet neural network as the fingerprint features of the emitter, and the identification of 10 radar emitter sources is completed. Based on the verification of real signals, the SEI identification strategy in this paper achieved a recognition rate of 96.4% for 10 radar signals, 98.9% for 10 data emitter signals, and 88.93% for 5 communication radio signals.

Recently, the unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) has become a highly sought-after topic for its wide applications in target recognition, detection, and tracking. However, SAR automatic target recognition (ATR) models based on deep neural networks (DNN) are suffering from adversarial examples. Generally, non-cooperators rarely disclose any SAR-ATR model information, making adversarial attacks challenging. To tackle this issue, we propose a novel attack method called Transferable Adversarial Network (TAN). It can craft highly transferable adversarial examples in real time and attack SAR-ATR models without any prior knowledge, which is of great significance for real-world black-box attacks. The proposed method improves the transferability via a two-player game, in which we simultaneously train two encoder–decoder models: a generator that crafts malicious samples through a one-step forward mapping from original data, and an attenuator that weakens the effectiveness of malicious samples by capturing the most harmful deformations. Particularly, compared to traditional iterative methods, the encoder–decoder model can one-step map original samples to adversarial examples, thus enabling real-time attacks. Experimental results indicate that our approach achieves state-of-the-art transferability with acceptable adversarial perturbations and minimum time costs compared to existing attack methods, making real-time black-box attacks without any prior knowledge a reality.

Recent studies have proven that synthetic aperture radar (SAR) automatic target recognition (ATR) models based on deep neural networks (DNN) are vulnerable to adversarial examples. However, existing attacks easily fail in the case where adversarial perturbations cannot be fully fed to victim models. We call this situation perturbation offset. Moreover, since background clutter takes up most of the area in SAR images and has low relevance to recognition results, fooling models with global perturbations is quite inefficient. This paper proposes a semi-white-box attack network called Universal Local Adversarial Network (ULAN) to generate universal adversarial perturbations (UAP) for the target regions of SAR images. In the proposed method, we calculate the model’s attention heatmaps through layer-wise relevance propagation (LRP), which is used to locate the target regions of SAR images that have high relevance to recognition results. In particular, we utilize a generator based on U-Net to learn the mapping from noise to UAPs and craft adversarial examples by adding the generated local perturbations to target regions. Experiments indicate that the proposed method effectively prevents perturbation offset and achieves comparable attack performance to conventional global UAPs by perturbing only a quarter or less of SAR image areas.

The radar signal intra-pulse clustering (RSIPC) can help achieve unsupervised radar emitter identification, which is of great significance in the field of electronic warfare. In order to address the poor performance of traditional clustering methods in handling RSIPC tasks, we propose a contrastive learning-based RSIPC method called CLIPC. Since the single-domain information of radar signal intra-pulses may result in the loss of important features, we integrate the multi-domain information of radar signal intra-pulses to obtain information fusion samples. By training a contrastive learning network on these information fusion samples, the network can extract deep features of radar signal intra-pulses. Subsequently, we realize RSIPC using these deep features. To enhance the adaptability of the used contrastive learning network, we optimize the data augmentation methods in the network through experimental analysis. Additionally, we optimize the dimension of the deep features extracted by the network to reduce information redundancy and improve the efficiency of features clustering. Experimental results demonstrate that our improvements in contrastive learning network lead to better clustering performance and efficiency. We also investigate the clustering performance and reliability of the CLIPC under different signal-to-noise ratios (SNRs) through experiments. When the SNR is 0dB, the proposed method has a clustering accuracy that is 0.1 higher than the contrastive learning method based on single-domain information, 0.3 higher than the traditional clustering method, and 0.2 higher than the clustering method based on auto-encoder.