Phishing attacks are a major threat to online security, exploiting user vulnerabilities to steal sensitive information. Various methods have been developed to counteract phishing, each with varying levels of accuracy, but they also face notable limitations. In this study, we introduce PhishAgent, a multimodal agent that combines a wide range of tools, integrating both online and offline knowledge bases with Multimodal Large Language Models (MLLMs). This combination leads to broader brand coverage, which enhances brand recognition and recall. Furthermore, we propose a multimodal information retrieval framework designed to extract the relevant top k items from offline knowledge bases, using available information from a webpage, including logos and HTML. Our empirical results, based on three real-world datasets, demonstrate that the proposed framework significantly enhances detection accuracy and reduces both false positives and false negatives, while maintaining model efficiency. Additionally, PhishAgent shows strong resilience against various types of adversarial attacks.

Abstract To address the issue of unremarkable targets and the serious loss of background details that occurs in multispectral image fusion, a multispectral image fusion method based on information decoupling is proposed. In accordance with the U‐shaped network structure, multi‐scale feature fusion is employed to obtain comprehensive contextual features. Subsequently, taking into account the differences between base and texture information in the images, the recovered image is reconstructed by fusing feature information through the information decoupling branches. Finally, the information decoupling is supervised by a loss function. In addition, a series of comparative experiments are conducted on a self‐constructed multispectral dataset and a publicly available dataset. Experimental results demonstrate that our method not only achieves higher fusion accuracy but also has superior visualization results.

Multi-network integration represents the future trend in measurement, control and communication. To provide optimal service, it is significant to study the network topology strategy of heterogeneous nodes. However, the mobility and node damage and failures caused by interference pose a huge challenge in reconfiguring the topology to ensure network performance. To address this issue, this paper proposes a topology reconfiguration algorithm based on minimum connectivity for a cross-domain multi-system measurement and control network, which integrates air, ground, and sea. This algorithm designs an optimal topology reconfiguration strategy considering connectivity, energy consumption, and position accuracy, and constructs a reliable measurement and control system. Meanwhile, by implementing the improved simulated annealing optimization, a robust measurement and control network topology can be obtained. Theoretical analysis and simulation results demonstrate that this algorithm can effectively resist external interference and ensure positioning accuracy, proved to be feasible and effective compared to the Global K-connected Energy-aware Topology-control Algorithm (GKETA) and greedy algorithm.

Satellite Internet technology is currently booming. Due to the high cost of satellites and the limited number of orbits, a satellite must cover a large area and serve more users than before. Given that the random access process is the initial step in establishing communication between satellites and terrestrial users, congestion control has emerged as a focal point of research. In this paper, we address the random access congestion control problem in satellite Internet scenarios and introduce the soft actor-critic (SAC) method to dynamically set the access class barring (ACB) factors. The throughput of random access is optimized to allow a single satellite to support a greater number of users without experiencing congestion. The SAC-ACB method is verified by simulation to converge faster and perform better than the proximal policy optimization (PPO) method.

Infrared (IR) small target detection under low signal-to-clutter ratio (SCR) is a fundamental and important problem in some critical missions like IR search and tracking (IRST). Though there exist a lot of works using local contrast measure (LCM) to detect the target, their performance are still unsatisfying due to the imperfect knowledge of target structure. In this letter, a novel IR small target detection method utilizing halo structure prior (HSP)-based LCM (HSPLCM) is proposed, which adequately considers the structure characteristic of the target. Specifically, through weighting the raw IR image via image structure tensor, we put forward a simple but useful image prior (named as HSP) which reflects the unique structural feature of the target to distinguish the real target and other background clutters. Afterward, based on this prior an effective LCM method is constructed to detect the IR small target, which can enhance the target and suppress the background clutters simultaneously. Furthermore, we extend the proposed algorithm to its multiscale version to solve the target scale uncertainty issues. Extensive experimental results have demonstrated that our proposed method favorably outperforms the state-of-the-arts.

X-ray crystallography is the main tool for structural determination of proteins. Yet, the underlying crystallization process is costly, has a high attrition rate and involves a series of trial-and-error attempts to obtain diffraction-quality crystals. The Structural Genomics Consortium aims to systematically solve representative structures of major protein-fold classes using primarily high-throughput X-ray crystallography. The attrition rate of these efforts can be improved by selection of proteins that are potentially easier to be crystallized. In this context, bioinformatics approaches have been developed to predict crystallization propensities based on protein sequences. These approaches are used to facilitate prioritization of the most promising target proteins, search for alternative structural orthologues of the target proteins and suggest designs of constructs capable of potentially enhancing the likelihood of successful crystallization. We reviewed and compared nine predictors of protein crystallization propensity. Moreover, we demonstrated that integrating selected outputs from multiple predictors as candidate input features to build the predictive model results in a significantly higher predictive performance when compared to using these predictors individually. Furthermore, we also introduced a new and accurate predictor of protein crystallization propensity, Crysf, which uses functional features extracted from UniProt as inputs. This comprehensive review will assist structural biologists in selecting the most appropriate predictor, and is also beneficial for bioinformaticians to develop a new generation of predictive algorithms.

Briefings in Bioinformatics 2017. doi: 10.1093/bib/bbx018. The authors would like to change the wording in their ‘Results and discussion’ section to remove the names of ‘ParCrys’ and ‘XANNpred’, which were identified as not having active webservers. The webservers for ParCrys and XANNpred are active and can be found at http://www.compbio.dundee.ac.uk/xtal and http://www.compbio.dundee.ac.uk/xannpred respectively. The authors apologize to the owners for the error which has been corrected.

The “Three River Headwaters” Region rangeland ecosystem is extremely sensitive and fragile, and in recent years has undergone continuous degradation. The vast nature and unfavorable natural conditions of the region inhibits data acquisition and field experiments resulting in different concepts about the spatial characteristics and dynamics of rangeland degradation. In this paper, a novel Local NPP Scaling (LNS) method was adopted to monitor the rangeland degradation in 1990 and 2004. Measured field data was used to verify the results of the degree of rangeland degradation. The percentage of rangeland degradation increased from 32.86% to 36.7% between 1990 and 2004 indicating 3.84% rate of degradation over 15 years. It is concluded through analyzing the results obtained with field surveying data and other research results that the spatial temporal distribution of the rangeland degradation at TRHR is reasonable, and the LNS method proved efficient and effective in rangeland degradation monitoring in this region.

Two strategies were developed to efficiently access and use the National Oceanic and Atmospheric Administration (NOAA) Comprehensive Large Array-data Stewardship System (CLASS) data repository with standard programming interfaces and specifications. One strategy, the selective duplication system (SDS), automatically duplicates data for focused areas. Another strategy, asynchronous data serving (ADS), serves data on demand. Both strategies have been implemented for serving data for algorithms using GOES data that detect and track severe weather events. Results showed the role of standards and well-known specifications. Data access delay is reduced. Interoperability is achieved.

s—The purpose of the paper was to find the solution to automatic acquisition and renewal of settlement feature from SPOT imagery. The solution consists of the following: one is feature extraction from imagery, the other is the cartographic generalization of the extracted features. Firstly, the extraction of residential area from SPOT image based on a decision tree model in combination with the analysis of characteristics of settlement and other land-use types on the image was discussed. Secondly, In terms of characteristics of extracted residential patches, a series of structuring elements were designed to remove the holes within patches, which were generated by complicated pixel grouping. Structuring elements were also designed for the morphological generalization of patch's corners and sides. Finally, based on point cluster simplification, a new method for residential patch selection was adopted, in which not only the requirements of selection count, spatial relationship between patches and their density contrast could be satisfied, but also the geometric feature of patches were considered. The result showed that the method discussed in the paper could be applied to rapid automatic extraction of vector geographical information on rural settlement and the information could meet the requirements of cartography. make cartographical generalization. Two steps must be done in the generalization of the settlement patches. One is the morphological generalization of settlement patch edge; the other is the selection of patches according to the scale, patch size and their spatial distribution (3-6). In this study, Jiangning county of Nanjing in China was taken as a case study area. Part of the test area is shown in Fig.4. The test area is typical of low mountains and hills and of complicated landscape. The image data of January 21, 1999 of SPOT-4 (XI) was used, which has 4 bands in total, two visible bands B1 (0.50~0.59µm), B2(0.61~0.68µm), one infrared band B3(0.78~0.89µm)and one short-wave infrared band SWIR(1.58~1.75µm).