LATIDIA · Ciberseguridad
¿Quién está detrás del arnés? Verificación de la identidad del modelo en los agentes de codificación mediante la huella digital del comportamiento
arXiv:2609.28559v2 Tipo de anuncio: sustitución Resumen: Los LLM funcionan cada vez más a través de sistemas de agentes de codificación que inspeccionan repositorios, invocan herramientas y modifican archivos. Sustituir el modelo que hay detrás de dicho agente puede...
WhatsApp ↗Telegram ↗
La noticia
arXiv:2609.28559v2 Announce Type: replace Abstract: LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files. Substituting the model behind such an agent can therefore change security-relevant decisions, including whether it verifies changes or recovers safely from failures. Existing LLM fingerprints largely infer identity from direct text or token distributions. In coding agents, these signals are mediated by system instructions, controller logic, tools, and execution feedback, limiting their transfer. We present LIDAR (LLM Identification from Decisions and Actions at Runtime), an active black-box fingerprinting method for coding-agent execution. Three coding probe pairs expose post-edit verification, transient-failure recovery, and specification--test conflict resolution under controlled changes. LIDAR represents the