The absorption and scattering of light in water usually result in the degradation of underwater image quality, such as color distortion and low contrast. Additionally, the performance of acquisition devices may limit the spatial resolution of underwater images, resulting in the loss of image details. Efficient modeling of long-range dependency is essential for understanding the global structure and local context of underwater images to enhance and restore details, which is a challenging task. In this paper, we propose an agent-guided non-local attention network using a multi-color space for underwater image enhancement and super-resolution. Specifically, local features with different receptive fields are first extracted simultaneously in the RGB, Lab, and HSI color spaces of underwater images. Then, the designed agent-guided non-local attention module with high expressiveness and lower computational complexity is utilized to model long-range dependency. Subsequently, the results from the multi-color space are adaptively fused with learned weights, and finally, the reconstruction block composed of deconvolution and the designed non-local attention module is used to output enhanced and super-resolution images. Experiments on multiple datasets demonstrated that our method significantly improves the visual perception of degraded underwater images and efficiently reconstructs missing details, and objective evaluations confirmed the superiority of our method over other state-of-the-art methods.

With the development of quantum computing, the application of quantum neural networks will be more and more extensive, and its security will also face more challenges. Although quantum communication has high security, quantum neural networks may have many internal and external insecure factors in the process of information transmission, such as noise impact during the preparation of input quantum states, privacy disclosure during transmission, and external attacks on the network structure, which may cause major security incidents. Because of the possible insecurity factors of quantum neural networks, this paper proposes a quantum sampling method to detect the state of quantum neural networks at each stage, so as to judge whether there are security risks in quantum neural networks and thus ensure their security. The method also provides a safe basis for further research on the stability and reliability of quantum neural networks.

Underwater images commonly experience degradation caused by light absorption and scattering in water. Developing lightweight and efficient neural networks to restore degraded images is challenging because of the difficulty in obtaining high-quality paired images and the delicate trade-off between model performance and computational demands. To provide a lightweight and efficient solution for restoring images in terms of color, structure, texture details, etc., enabling the underwater image restoration task to be applied in real-world scenes, we propose an unsupervised lightweight multi-branch context network. Specifically, we design two lightweight multi-branch context subnetworks that enable multiple receptive field feature extraction and long-range dependency modeling to estimate scene radiance and transmission maps. Gaussian blur is adopted to approximate the global background light on the twice-downsampled degraded image. We design a comprehensive loss function that incorporates multiple components, including self-supervised consistency loss and reconstruction loss, to train the network using degraded images in an unsupervised learning manner. Experiments on several underwater image datasets demonstrate that our approach realizes good performance with very few model parameters (0.12 M), and is even comparable to state-of-the-art methods (up to 149 M) in color correction and contrast restoration.

Quantum neural networks (QNNs) leverage the strengths of both quantum computing and neural networks, offering solutions to challenges that are often beyond the reach of traditional neural networks. QNNs are being used in areas such as computer games, function approximation, and big data processing. Moreover, quantum neural network algorithms are finding utility in social network modeling, associative memory systems, and automatic control mechanisms. Nevertheless, ensuring the reliability of quantum neural networks is crucial as it directly influences network performance and stability. To investigate the reliability of quantum neural networks, this paper proposes a methodology wherein operator measurements are performed on the final states of the output quantum states of a quantum neural network. The proximity of these measurements to the target value is compared, and the fidelity value, combined with a quantum gate operation, is utilized to assess the reliability of the quantum neural network. Through network training, the results demonstrate that, under optimal parameters, both the fidelity of the final state measurement value and the target value of the model approach are approximately equal to 1. It indicates that training mitigates the errors stemming from encoding into the initial quantum state, thereby resulting in enhanced system reliability and accuracy.

Security research in quantum neural networks (QNNs) is an emerging field that aims to utilize the principles of quantum mechanics to protect the security of neural networks, and this protection can be against different threats such as eavesdropping, tampering, and malware attacks. Backdoor attacks are a serious security challenge in the field of deep neural networks. This type of attack is highly stealthy and harmful, which can silently implant malicious functions and trigger them under specific conditions, thus disrupting the normal operation of neural networks or leaking sensitive information. To address the potential security risks of backdoor attacks to QNNs, this paper focuses on two core issues: backdoor attack detection and defense strategy design. It proposes an activation-based clustering method for backdoor sample detection (ACDM) to counter backdoor attack threats. Experimental results demonstrate that this defense method effectively safeguards the operational security of QNNs while enhancing the model's robustness against abnormal inputs and the reliability of its output results. It should be noted that the current research has limitations: the adaptability and effectiveness of this defense framework on complex high-dimensional datasets (e.g., quantum image datasets) and QNNs with different topological structures (e.g., deep quantum convolutional networks) require further validation and optimization through subsequent experiments.

In response to the current research landscape, which lacks unified quantitative standards and a reproducible verification framework for assessing the security of quantum neural networks (QNNs), this paper proposes a quantitative evaluation system and verification scheme for QNN security based on the violation characteristics of CHSH-type Bell inequalities. This method treats quantum entanglement as the core element of intrinsic security and establishes a controlled-variable controlled experiment involving purely classical models, non-entangled QNNs, weakly entangled QNNs, and strongly entangled QNNs. Numerical simulations were conducted using the Iris dataset; the presence of quantum entanglement was determined using the CHSH statistic, and a quantitative metric system centered on the normalized CHSH observation metric Q was constructed. Based on the theoretical limits of Bell’s inequalities, a normalization derivation was performed to establish the theoretical constraint interval of $0\le \mathrm{Q}\le 1$; the threshold values of 0.3 and 0.7 obtained from the simulations are applicable only to the experimental scenarios described in this paper and serve solely as a reference for grouping data within the experiment; they do not possess universal validity for determination. Simulation results show that the CHSH values for the weakly and strongly entangled QNN experimental groups can reach 2.8284, significantly exceeding the theoretical limits of classical locality. These values correspond to an observation metric of $Q=0.9838$ and a privacy protection strength of $P=0.8854$, with the security level rated as high. The CHSH values of the non-entangled QNN and the purely classical model do not exceed the classical threshold of 2; they exhibit no quantum nonlocality or quantum advantage, and their security level is rated as low. This paper advances the security evaluation of QNNs from qualitative, empirical judgments to verifiable quantitative classification, providing a theoretical basis and evaluation framework for the practical application of quantum neural networks in highly security-sensitive scenarios such as privacy-preserving computing.