Metalens can achieve arbitrary light modulation by controlling the amplitude, phase, and polarization of the incident waves and have been applied across various fields. This paper presents a color router designed based on metalens, capable of effectively separating spectra from visible light to near-infrared light. Traditional design methods for meta-lenses require extensive simulations, making them time-consuming. In this study, we propose a deep learning network capable of forward prediction across a broad wavelength range, combined with a particle swarm optimization algorithm to design metalens efficiently. The simulation results align closely with theoretical predictions. The designed color router can simultaneously meet the theoretical transmission phase of the target spectra, specifically for red, green, blue, and near-infrared light, and focus them into designated areas. Notably, the optical efficiency of this design reaches 40%, significantly surpassing the efficiency of traditional color filters.

The threat posed by adversarial examples (AEs) to deep learning applications has garnered significant attention from the academic community. In response, various defense strategies have been proposed, including adversarial example detection. A range of detection algorithms has been developed to differentiate between benign samples and adversarial examples. However, the detection accuracy of these algorithms is significantly influenced by the characteristics of the adversarial attacks, such as attack type and intensity. Furthermore, the impact of image preprocessing on detection robustness—a common step before adversarial example generation—has been largely overlooked in prior research. To address these challenges, this paper introduces a novel adversarial example detection algorithm based on high-level feature differences (HFDs), which is specifically designed to improve robustness against both attacks and preprocessing operations. For each test image, a counterpart image with the same predicted label is randomly selected from the training dataset. The high-level features of both images are extracted using an encoder and compared through a similarity measurement model. If the feature similarity is low, the test image is classified as an adversarial example. The proposed method was evaluated for detection accuracy against four comparison methods, showing significant improvements over FS, DF, and MD, with a performance comparable to ESRM. Therefore, the subsequent robustness experiments focused exclusively on ESRM. Our results demonstrate that the proposed method exhibits superior robustness against preprocessing operations, such as downsampling and common corruptions, applied by attackers before generating adversarial examples. It is also applicable to various target models. By exploiting semantic conflicts in high-level features between clean and adversarial examples with the same predicted label, the method achieves high detection accuracy across diverse attack types while maintaining resilience to preprocessing, providing a valuable new perspective in the design of adversarial example detection algorithms.

As a new high-resolution spaceborne SAR observation mode, sliding-spot imaging has the characteristics of a large squint, long aperture time, and azimuth aliasing, and because of the dechirp operation in the imaging algorithm of this mode, it is difficult to construct a direct range–Doppler equation for its geometric processing. In this paper a conformation model based on an antenna pointing vector is presented, which fully considers the influence of the dechirp operation on the range image, starts from the relative position of the dechirped range image points and the satellite, and establishes a strict conversion model between the image coordinates and geographic coordinates using the accurate satellite–ground geometric conditions. Then the forward and reverse formulas for geometric processing of the sliding-spot mode are given based on this model. Finally, geometric calibration and positioning experiments under different conditions and field spaceborne SAR data are executed. Results show that after geometric errors caused by the SAR payload have been calibrated and other factors such as atmospheric delay, platform position, and elevation error have been compensated, the uncontrolled geometric positioning accuracy can reach within 1 m–2 m, which fully proves the effectiveness of this method in the geometric positioning of high-resolution sliding-spot images.