LATIDIA · Ciberseguridad

Seguridad y privacidad en agentes incorporados impulsados por modelos grandes: ataques, defensas y direcciones futuras

arXiv: 2609.27847v1Tipo de anuncio: nuevo Resumen: Los agentes incorporados impulsados por modelos grandes integran los modelos de base con la percepción, el razonamiento, la planificación y la acción física, extendiendo los riesgos convencionales a nivel de modelo a embo

La noticia

arXiv:2609.27847v1 Announce Type: new Abstract: Large-model-driven embodied agents integrate foundation models with perception, reasoning, planning, and physical action, extending conventional model-level risks into embodied closed loops. Existing studies on their security and privacy remain fragmented across different system components and operational stages, making it difficult to understand how risks arise, propagate, and ultimately affect physical behavior or sensitive information. This survey presents a lifecycle-based analysis of security and privacy in large-model-driven embodied agents. We organize existing research into five stages: model construction and supply chain, multimodal input and interaction, semantic reasoning and task planning, action execution and physical feedback, and long-term deployment. Within this lifecycle, we systematically review representative attacks,