LATIDIA · Ciberseguridad

InferD: un marco Honeypot para la infraestructura de inferencia de IA

arXiv: 2610.39807v1Tipo de anuncio: nuevo Resumen: el modelo de lenguaje grande que sirve a las pilas, las API de inferencia comercial, las bases de datos vectoriales y las puertas de enlace de orquestación de agentes ahora se exponen en la Internet pública e indexan por c

La noticia

arXiv:2610.39807v1 Announce Type: new Abstract: Large language model serving stacks, commercial inference APIs, vector databases, and agent orchestration gateways are now ex- posed on the public internet and indexed by commodity scanners within hours of deployment. The threat characteristics of this sur- face are only beginning to be measured, and the honeypot frame- works that could measure it were designed for conventional net- work services rather than for AI infrastructure. In fact, emulating an AI service is a distinct deception problem: the observable behavior of the service, including model inventories, token formats, tool-call protocols, and authorization flows, must be reproduced faithfully, while the underlying computation, model inference and tool ex-