The rapid growth of blockchain technology and the increasing number of network nodes have heightened the risk of sophisticated attacks. Among these, Eclipse attacks present a serious threat to decentralized networks by exploiting their peer-to-peer structures. While previous research has explored artificial intelligence techniques to defend against Eclipse attacks, evolving attack patterns continue to challenge existing defenses. In this paper, we propose a novel defense framework that integrates a clustering approach based on self-attention encoders within a multi-kernel neural network clustering model. Our method utilizes parallel subnetworks to extract category-specific features from multiple perspectives, generating discriminative cluster centroids that are combined with raw transaction data to train a robust classifier for detecting Eclipse attacks in Ethereum networks. To evaluate our approach, we simulate Eclipse attacks on the Ethereum testnet and conduct extensive experiments. The results demonstrate that our method achieves a detection accuracy of 98.5% and improves classification performance by 5% compared to models trained without cluster-enhanced features, confirming the effectiveness of the proposed defense.

Visual recognition models have achieved unprecedented success in various tasks. While researchers aim to understand the underlying mechanisms of these models, the growing demand for deployment in safety-critical areas like autonomous driving and medical diagnostics has accelerated the development of eXplainable AI (XAI). Distinct from generic XAI, visual recognition XAI is positioned at the intersection of vision and language, which represent the two most fundamental human modalities and form the cornerstones of multimodal intelligence. This paper provides a systematic survey of XAI in visual recognition by establishing a multi-dimensional taxonomy from a human-centered perspective based on intent, object, presentation, and methodology. Beyond categorization, we summarize critical evaluation desiderata and metrics, conducting an extensive qualitative assessment across different categories and demonstrating quantitative benchmarks within specific dimensions. Furthermore, we explore the interpretability of Multimodal Large Language Models and practical applications, identifying emerging trends and opportunities. By synthesizing these diverse perspectives, this survey provides an insightful roadmap to inspire future research on the interpretability of visual recognition models.

Recent advances in cooperative driving have garnered significant attention, as it is believed to have greater potential than single-vehicle systems in complex environments. However, gaps in current research frameworks impede its further development. Dataset-based frameworks provide a limited perspective, failing to capture the dynamic, asynchronous, and interactive complexities of the real world. Simulation-based frameworks often employ synchronous implementation and oversimplified communication models, impeding meaningful real-time performance evaluation in asynchronous environments. To this end, we propose RAMACoDrive, a novel real-time asynchronous framework for cooperative perception research. RAMACoDrive implements complete process separation, allowing agents and their internal components to operate asynchronously and independently. It uniquely integrates hardware-in-the-loop V2X communication using an external device for realistic data forwarding. Furthermore, RAMACoDrive incorporates an asynchronous online evaluation method with real-time performance metrics, enabling comprehensive evaluation beyond mere accuracy. Through experiments centered on cooperative 3D object detection, we demonstrate its effectiveness in revealing the impact of real-world asynchronous effects and communication constraints. RAMACoDrive provides a valuable and realistic testbed for cooperative perception algorithms and helps to advance the deployment of practical applications. The code will be released on our GitHub repository.

Affected by the Coronavirus Disease (COVID-19) pandemic, almost all students in China have to study online at home from February to June, 2020. In this paper, we discussed the forms of online courses and took Jiangsu Normal University as an example to introduce the online courses of remote sensing in China. The results of the satisfaction survey show that more than 90% of the respondents agree with online courses and believe that online courses can at least meet basic learning needs in the age of COVID-19, and more than 60% of respondents claimed that they had met or exceeded their learning expectations. The major advantages of online course include reducing the gathering of people and thus the risk of infection. However, there are still some problems with online courses, and we hope that these problems can be solved well in the future.

In this paper, an algorithm of the land surface bidirectional reflectance distribution function (BRDF) and albedo parameters inversion is proposed based on a simplified atmospheric radiative transfer model coupling with the BRDF model. The algorithm is applied to the Sentinel-2 Multi-Spectral Instrument (MSI) data. To validate the inversion, the BRDF/ albedo parameters derived from the MODerate Resolution Imaging Spectroradiometer (MODIS) were collected and resampled to match the MSI data. The preliminary validation shows a good consistency between the two datasets with the correlative coefficient (R) greater than 0.8 and the root-mean-square error (RMSE) less than 0.05 for the red and near infrared bands. The advantage of this algorithm is that the spatial resolution of the satellite-derived BRDF/albedo parameters can be improved as high as 20 m, which has great potential in quantitative remote sensing applications.