LATIDIA · Ciberseguridad

TARIFA: Estimación de la región de aceptación forense para atrapar generadores de imágenes de cebo y cambio

arXiv: 2609.30982v1Tipo de anuncio: Cross Resumen: Los generadores de imágenes de IA modernos se implementan cada vez más como API opacas, donde los clientes pueden consultar el servicio implementado, pero no pueden inspeccionar los pesos o la arquitectura del modelo. Thi

La noticia

arXiv:2609.30982v1 Announce Type: cross Abstract: Modern AI image generators are increasingly deployed as opaque APIs, where customers can query the deployed service, but cannot inspect model weights or architecture. This creates a practical challenge: a provider may pass governance certification with one generator and later silently switch to a cheaper and lower-quality one for deployment, compromising public trust or even safety in high-stakes domains. We study integrity auditing at deployment time and propose FARE (Forensic Acceptance Region Estimation). A certified generator is enrolled by training FARE on images sampled from that generator. After deployment, FARE can determine whether a generated image is consistent with the enrolled generator---using only that image.