The rapid expansion of Low Earth Orbit (LEO) satellite constellations has brought significant spectrum management challenges, including spectrum scarcity and complex interference issues. Traditional algorithms and prior Artificial Intelligence (AI) methods fail to meet LEO’s demands for managing extreme dynamics, massive scale, and multi-objective optimization. This paper introduces an innovative Large Language Model (LLM) framework for intelligent spectrum sharing and dynamic resource allocation in satellite-terrestrial down-link systems. First, we established a geometric model for satellite-terrestrial down-link communication, and accurately derived the statistical distribution function of satellites within the space enclosed by a specific orbital line by combining the stochastic geometry theory. Under this geometric model, a communication scenario was introduced, and an adaptive modulation transmission mechanism based on orthogonal frequency division multiplexing signals was designed. Then, the system combines the real-time spectrum sensing results with the natural language description of the quality of service of multi-service data using prompt engineering techniques, and delivers the comprehensive information to the LLM for resource allocation and generation of a transmission scheme. Finally, the resource allocation and transmission scheme determined by the LLM is applied to the established communication model, and the system performance is comprehensively evaluated by analyzing indicators such as outage probability, system throughput, and transmission and waiting delays. Primary contributions include novel dynamic service-to-strategy generation, an LLM-centric prompt-driven architecture, and a new paradigm that positions the LLM as an intelligent “spectrum orchestration brain” for complex global LEO resource management. Collectively, these advancements enhance spectrum utilization intelligence, adaptability, and efficiency, offering a transformative approach to overcome the limitations of prior methods in demanding LEO environments.

Low Earth Orbit (LEO) satellite systems with sensing capabilities are widely regarded as promoting reliable and efficient communication services globally. This paper proposes a Multi-Satellite Collaborative Security System with Integrated Sensing and Communication (ISAC-MSC). Considering the potential benefits of LEO satellites and ISAC, we exploit sensing performance in the MSC system by jointly optimizing LEO satellite assignments, communication Beamforming (BF) vectors, and sensing BF vectors. Specifically, we design improved Continuous Particle Swarm (CP) optimization and Discrete Particle Swarm (DP) optimization algorithms to maximize the target sensing Signal-to-Noise Ratio (SNR) for LEO satellite assignments. Additionally, with respect to the BF vector optimization, we develop Power Approximation (PA) optimization algorithm, Inner Approximation (IA) optimization algorithm, and Joint Sensing and Communication BF (JSC-BF) optimization algorithm. Multiple algorithms are tightly integrated and alternately iterated. Numerical results show that: 1) the JSC-BF algorithms outperform the PA and IA algorithms in terms of sensing performance and communication secrecy rate; 2) compared to the single satellite case, the ISAC-MSC system performance approximately linear growth, and has strong extensibility; 3) with imperfect MSC synchronization case, the communication secrecy rate appears inflection point and stabilization, but the JSC-BF algorithms still have excellent performance.

The past decade has witnessed the wide adoption of AI code generators, such as GitHub Copilot, AskCodi, and OpenAI Codex. They offer intelligent solution code for code completion to achieve faster development, cleaner code, and a significant boost in overall productivity. However, such significant productivity advantages also inadvertently lead to the generation of insecure solution code because most AI code generators derive their knowledge from existing projects, which typically prioritize functionality over security. Although numerous tools have been developed to integrate with the code generators for identifying vulnerabilities, the inconsistency in syntactic features and variability in coding rules make the detection task challenging across different programming languages. To address the challenges, we devise a prompt-enhancing approach, PECKER. It examines textual prompts provided by users to identify risky prompts that could lead to insecure code generation. Given the risky prompts, PECKER conducts security-centric rewriting to strengthen the "potentially insecure" descriptions, thereby guiding AI code generators in mitigating vulnerabilities during code generation. We integrated PECKER with one of the most prevalent AI code generators, GitHub Copilot for evaluation. Among 509 risky prompts, PECKER successfully identified and rectified 471 risky prompts.

Space-air-ground integration has become paramount in the next generation of wireless communication systems in the era marked by the seamless integration of terrestrial and celestial domains. On the other hand, the age of information (AoI) has recently emerged as a vital metric for evaluating the timeliness and freshness of data in these multi-hop communication systems. This paper focuses on investigating the information freshness of multi-hop satellite IoT systems while considering several automatic repeat request (ARQ) and hybrid ARQ (HARQ) schemes over different hops to promise the reliability of data transmissions. Specifically, a group of remote sensors transmits their data to a terrestrial base station (B) via the code-division multiple access (CDMA) strategy to exploit CDMA’s natural merits, e.g., anti-jamming and simultaneous transmissions. Then, B sends these received data to a data destination (D) via a satellite (R) under the transparent forwarding strategy. We derive the closed form of the outage probability for the CDMA protocol considering multi-user interference (MUI) and the closed form of the end-to-end outage probability for the three kinds of ARQ and HARQ schemes on the dual-hopB-R-Dtransmission, and then finally derive the expression of the corresponding AoI. Finally, numerical results show that simulations match well with the theoretical results, proving the analysis’s correctness and the pros and cons of the different ARQ/HARQ schemes.

Low Earth orbit (LEO) Mega-constellations have emerged as a transformative approach to realize enhanced system capacity and improved coverage to satisfy the ever-increasing global demand for data services. Subsequently, the high density of satellites in a confined orbital region poses challenges, including potential interference among neighboring satellites. Further, it is vital to adequately address the impacts of safety distances in satellite communication systems on ensuring proper operation, collision avoidance, and interference management. Inspired by these observations, this work proposes a novel analysis tool, the Poisson arc hardcore point process (PAHPP), by extending the traditional Poisson line hardcore point process to characterize the unique orbiting properties of the satellites in LEO mega-constellations, accounting for factors such as the orbit, the satellite density, and spatial distribution. Specifically, this paper presents the PAHPP by enforcing a minimum separation between satellites operating in the same circular orbit to reflect the practical LEO mega-constellations. The imposed minimum inter-satellite separation in the proposed PAHPP model has also been applied to multi-orbit multi-satellite communication cases. Moreover, the discretization approximation technique is employed to analyze system performance, focusing on serving distance and outage probability. Numerical results provide valuable insights and conclusions for uncovering and recognizing LEO mega-constellations.

Existing OCR engines or document image analysis systems typically rely on training separate models for text detection in varying scenarios and granularities, leading to significant computational complexity and resource demands. In this paper, we introduce "Detect Any Text" (DAT), an advanced paradigm that seamlessly unifies scene text detection, layout analysis, and document page detection into a cohesive, end-to-end model. This design enables DAT to efficiently manage text instances at different granularities, including word, line, paragraph and page. A pivotal innovation in DAT is the across-granularity interactive attention module, which significantly enhances the representation learning of text instances at varying granularities by correlating structural information across different text queries. As a result, it enables the model to achieve mutually beneficial detection performances across multiple text granularities. Additionally, a prompt-based segmentation module refines detection outcomes for texts of arbitrary curvature and complex layouts, thereby improving DAT’s accuracy and expanding its real-world applicability. Experimental results demonstrate that DAT achieves state-of-the-art performances across a variety of text-related benchmarks, including multi-oriented/arbitrarily-shaped scene text detection, document layout analysis and page detection tasks.

This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT that consists of three major challenges: i) scene text detection, ii) scene text recognition, and iii) scene text spotting. A total of 78 submissions from 46 unique teams/individuals were received for this competition. The top performing score of each challenge is as follows: i) T1 - 82.65%, ii) T2.1 - 74.3%, iii) T2.2 - 85.32%, iv) T3.1 - 53.86%, and v) T3.2 - 54.91%. Apart from the results, this paper also details the ArT dataset, tasks description, evaluation metrics and participants' methods. The dataset, the evaluation kit as well as the results are publicly available at the challenge website.

Robust text reading from street view images provides valuable information for various applications. Performance improvement of existing methods in such a challenging scenario heavily relies on the amount of fully annotated training data, which is costly and in-efficient to obtain. To scale up the amount of training data while keeping the labeling procedure cost-effective, this competition introduces a new challenge on Large-scale Street View Text with Partial Labeling (LSVT), providing 5,0000 and 400,000 images in full and weak annotations, respectively. This competition aims to explore the abilities of state-of-the-art methods to detect and recognize text instances from large-scale street view images, closing gaps between research benchmarks and real applications. During the competition period, a total number of 41 teams participate in the two tasks with 132 valid submissions, i.e., text detection and end-to-end text spotting. This paper includes dataset descriptions, task definitions, evaluation protocols and results summaries of ICDAR 2019-LSVT challenge.

This paper presents a model named Multi-Scale YOLOv2 (MS-YOLOv2) for hand detection in complex scenes. The proposed MS-YOLOv2 is implemented by introducing three modules to YOLOv2, including a Multi-Scale Feature Refinement Module to acquire fine-grained features, a Channel Importance Evaluation Module to recalibrate feature channels and a Hard Example Punishment Module to get rid of hand interference areas. Experiment results show that the proposed MS-YOLOv2 makes much performance improvement to YOLOv2, but with little computational complexity gain. On our dataset, the proposed MS-YOLOv2 can achieve 98.2% of AP and 97.9% of AR. Moreover, on the VIVA challenge, the proposed MS-YOLOv2 achieves AP/AR of 85.1%/45.8% at Level-1 and 80.1%/45.9% at Level-2.

This paper proposes an efficient model named Light YOLO for hand gesture recognition on the embedded platforms. Light YOLO improves accuracy, speed, and model size, in three aspects. To deal with the small scale gestures in practical applications, we strengthen the YOLOv2 with a spatial refinement module to obtain fine-grained features. To accelerate the refined network, we propose a selective-dropout channel pruning approach to prune the redundancy convolution kernels in the network. Moreover, we introduce a dataset for hand gesture recognition in complex scenes. The experimental results on this dataset show that the proposed Light YOLO significantly improve the YOLOv2 network, i.e., accuracy from 96.80% to 98.06%, speed form 40PFS to 125FPS, and size form 250M to 4MB.