LATIDIA · Ciberseguridad

Defensa en Profundidad en la Interfaz de Percepción-Razonamiento de Enjambres de UAV Agénicos Centrados en LLM

arXiv: 2610.03319v1Tipo de anuncio: nuevo Resumen: los modelos de lenguaje grande (LLM) admiten cada vez más operaciones de enjambre de vehículos aéreos no tripulados (UAV), como la programación de recopilación de datos, donde el modelo lee el sensor estructurado

La noticia

arXiv:2610.03319v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly support Uncrewed Aerial Vehicle (UAV) swarm operations such as data collection scheduling, where the model reads structured sensor reports and decides which sensors to visit. An adversary who quietly manipulates those reports can redirect the swarm without modifying the model weights or the UAV. Defenses for this interface have been proposed architecturally but rarely implemented or evaluated. We implement and evaluate defense-in-depth at the perception-reasoning interface of LLM-Centric Agentic UAV Swarms. Five layers check the provenance of a report, whether its values are physically admissible, whether they agree with what swarm geometry and service history predict, whether the resulting schedule