In this paper, to address the problem of array sensors failure, we propose a covariance matrix reconstruction method for direction-of-arrival (DOA) estimation. Firstly, we devise a diagnosis method to detect and locate the positions of failure sensors. According to the robustness of the array, the sensor failure scenarios are classified into redundant sensors failure and non-redundant sensors failure. Then, the corresponding DOA estimation method is adopted for two failure scenarios. The former can be solved using the virtual sensors in the difference coarray. As for the latter, the difference coarray has some holes, resulting in the decrease of available continuous virtual sensors or degrees of freedom (DOFs). Based on the matrix completion theory, the covariance matrix is extended to a high-dimensional Toeplitz matrix with missing data, where some elements are zero. We employ the mapping matrix, further use trace norm instead of the rank norm for convex relaxation to reconstruct the covariance matrix, thereby realizing the filling of the virtual sensor holes in difference coarray and restoring the DOFs. Compared with the sparsity-based methods, the proposed method can eliminate the effect of the discretization of the angle domain, and avoid regularization parameter selection. Finally, the root-MUSIC method is given for DOA estimation. Theoretical analysis and simulation results show that the proposed methods can alleviate the effect of array sensors failure and improve the estimation performance.

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.

The development of Internet technology has provided great convenience for data transmission and sharing, but it also brings serious security problems that are related to data protection. As is detailed in this paper, an enhanced steganography network was designed to protect secret image data that contains private or confidential information; this network consists of a concealing network and a revealing network in order to achieve image embedding and recovery separately. To reduce the system’s computation complexity, we constructed the network’s framework using a down–up structure in order to compress the intermediate feature maps. In order to mitigate the input’s information loss caused by a sequence of convolution blocks, the long skip concatenation method was designed to pass the raw information to the top layer, thus synthesizing high-quality hidden images with fine texture details. In addition, we propose a novel strategy called non-activated feature fusion (NAFF), which is designed to provide stronger supervision for synthetizing higher-quality hidden images and recovered images. In order to further boost the hidden image’s visual quality and enhance its imperceptibility, an attention mechanism-based enhanced module was designed to reconstruct and enhance the salient target, thus covering up and obscuring the embedded secret content. Furthermore, a hybrid loss function that is composed of pixel domain loss and structure domain loss was designed to boost the hidden image’s structural quality and visual security. Our experimental results demonstrate that, due to the elaborate design of the network structure and loss function, our proposed method achieves high levels of imperceptibility and security.

In this paper, to improve the utilization of noncontiguous virtual sensors of the coprime array, we propose a covariance matrix reconstruction method for underdetermined direction-of-arrival (DOA) estimation. Firstly, the distribution characteristic of virtual sensors is analyzed from the perspective of the difference coarray. According to the correspondence between the difference coarray and the wave path difference, the covariance matrix is extended to a high-dimensional Toeplitz covariance matrix with missing data. Then, based on the matrix completion theory, we employing the mapping matrix, further use trace norm instead of the rank norm for convex relaxation to recover the matrix, thereby realizing the filling of the virtual sensor holes. Compared with the sparsity- based methods, the proposed method can eliminate the effect of the discretization of the angle domain.

In recent years, the unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) has become a highly sought-after topic for its wide applications in the field of 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 information about SAR-ATR models, making adversarial attacks challenging. In this situation, we propose Transferable Adversarial Network (TAN) to attack these models with highly transferable adversarial examples. 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. In particular, compared to traditional iterative methods, our approach is able to one-step map original samples to adversarial examples, thus enabling real-time attacks. Experimental results indicate that the proposed approach achieves state-of-the-art transferability with acceptable adversarial perturbations and minimum time costs compared to existing attack methods, i.e., it excellently realizes real-time transferable adversarial attacks.

The performance of direction of arrival (DOA) estimation degrades in the case of sensor failures. To solve this problem, a virtual array DOA estimation method based on covariance matrix completion is proposed. First, the covariance matrix is extended to a high-dimensional covariance matrix to construct a virtual array. Then, the matrix completion problem is constructed, and the extended covariance matrix is completed by the OptSpace method. Finally, using the obtained target matrix, DOA estimation is performed based on the root-MUSIC method. Theoretical and simulation results show that the proposed method can effectively restore the estimation accuracy in the sensor failure scenario.