Satellite networks and space–ground integrated systems increasingly carry traffic over links that are exposed to cyberattacks. Among these threats, Distributed Denial-of-Service (DDoS) attacks are especially harmful. They saturate inter-satellite links and reduce transmission efficiency, and they can stall onboard communication services. Deep learning detectors handle such attacks well on the ground, but most depend on high-dimensional features and quadratic attention, whose compute and memory requirements exceed a satellite’s budget. We present LiteSat-Attn, a lightweight temporal anomaly detector based on a pseudo-attention mechanism. It reads only two link-observable features, packet length and inter-arrival time. Rather than computing Query-Key-Value (QKV) projections, it applies a pointwise (1×1) convolutional gating module to produce an adaptive temporal mask. The mask is trained jointly with the detection objective, so the model emphasizes anomalous time steps at negligible extra cost. On CICIDS2017 and DoHBrw2020, LiteSat-Attn reaches 99.67% and 99.62% accuracy while using 0.10M parameters, 0.40 MB of storage, and little inference compute. Its accuracy stays competitive with far heavier models while fitting the resource limits of satellite-side and other constrained deployments.
Model predictive control (MPC) of servo motors is sensitive to parameter mismatch and load disturbance, as the prediction law relies on an accurate plant model. To address this issue, we propose a robust position MPC scheme with a noise-suppressed disturbance observer. Starting from the servo-motor dynamics, we establish a lumped disturbance model of the current and speed loops by a truncated Taylor expansion, which accounts for electrical-parameter variations, mechanical-parameter variations and load changes. The resulting disturbance model is used to reconstruct both the position-servo prediction model and the associated linear constraints. For the current and speed disturbance channels, generalized proportional–integral observers with embedded first-order filtering are designed so that the disturbance and its first derivative can be estimated with improved high-frequency noise attenuation. The estimated quantities are employed online to compensate the prediction model and to correct the constraint bounds. A constrained convex program, comprising an integrated position–speed–current cost and the corrected inequality constraints, is then solved by the Hildreth algorithm and applied to the inverter through space-vector pulse-width modulation. Comparative experiments on a surface-mounted permanent-magnet servo platform demonstrate that the proposed method improves positioning performance under parameter mismatch and load disturbance.
The development of clean and sustainable energy has become a global focus, with nuclear energy playing an important role in low-carbon energy systems. To address the complex cable routing problem in nuclear island environments, this study proposes a three-dimensional cable routing optimization framework based on an improved A* algorithm. The proposed method incorporates multiple engineering-related constraints, including cable type, protection level, turning angle, and construction standards, while optimizing routing paths in constrained spatial environments. A simplified spatial expansion strategy is adopted to approximate routing safety margins while maintaining computational efficiency. Experimental results demonstrate that the proposed method effectively reduces the number of bends and shortens routing paths under predefined engineering constraints, thereby improving routing efficiency and reducing installation costs. The proposed framework provides a preliminary engineering-oriented routing optimization approach and preserves extensibility for future integration of thermal dissipation and electromagnetic compatibility constraints.
Open-source vulnerability evidence is distributed across vulnerability databases, project advisories, version records, code repositories, issue/PR threads, proofs of concept, and tests. These artifacts may share upstream sources, apply to different scopes, or contain inconsistent conclusions, while security fixes may evolve through backports, follow-up fixes, bypass fixes, and cross-branch variants. This paper investigates a multi-source evidence-driven framework for representing and recovering vulnerability conditions in open-source components. The method normalizes heterogeneous artifacts into provenance-, time-, and scope-anchored atomic claims, constructs patch families to recover scope-aware fix invariants, and applies temporal–scope constraints to model evolutionary supersession, alternative triggers, and genuine conflicts while preserving Unknown or Conflict states. We conduct a mechanism-oriented evaluation on 75 real vulnerabilities with traceable project-side evidence from the Maven, PyPI, and Go ecosystems. The complete framework does not outperform simpler baselines on overall condition recovery or demonstrate a consistent advantage in fix-invariant recovery. On cases containing Unknown conditions, abstention reduces Unknown-to-Known errors at the cost of determinate coverage; patch-relation and genuine-Conflict recovery remain unsuccessful in the present evaluation. The results characterize the limits of the current framework and identify specific trade-offs and unresolved requirements for evidence-grounded repair and uncertainty reasoning.
Swarm robotics (SR) and swarm intelligence (SI) share decentralization and collective behavior but address different problems. SR concerns physical multi-robot systems whose collective behavior must hold under sensing, communication, energy, and safety constraints, while SI includes computational models and optimization methods, many of which involve no robots. Conflating them obscures which SI results transfer to robot swarms and what machine learning (ML) contributes. This review examines SR coordination, SI optimization, and ML-augmented hybrid methods from a deployment perspective. It proposes a tiered framework for deciding whether a system is a robotic swarm, a taxonomy of five hybrid SR–SI–ML architecture types, and feasibility conditions for combining methods on a given platform. Across 17 coded studies, SI optimizers such as Ant Colony Optimization and Particle Swarm Optimization are evaluated mainly on benchmarks or in simulation and reach hardware only with supporting infrastructure; hardware experiments, with one exception, use twenty robots or fewer, and learned controllers transfer to hardware in some studies but show a large simulation-to-reality gap in others. Layered hybrid architectures, in which SR provides coordination, SI provides optimization and ML provides adaptation, remain a design hypothesis. The review proposes a reporting checklist for future studies.
