LATIDIA · Ciberseguridad

Detección de la capacitación en IA en Datacenter Power

arXiv: 2610.30182v1Tipo de anuncio: nuevo Resumen: los acuerdos de gobernanza de IA requieren métodos para detectar ejecuciones de capacitación de modelos grandes en un clúster informático monitoreado, sin confiar en el operador. Desarrollamos un método para detectar

La noticia

arXiv:2610.30182v1 Announce Type: new Abstract: AI governance agreements require methods to detect large model training runs on a monitored computing cluster, without trusting the operator. We develop a method to detect synchronous model training in facility-level power by Viterbi tracking of the wandering iteration cadence. On simulated datacentre power, when the operator makes no attempt to hide, the Viterbi tracker detects at least $96\%$ of training runs against a declared inference workload, at a $1\%$ false-alarm rate and within $0.04$ of the Neyman--Pearson optimum, given a meter that samples at $2$ Hz or faster. Of eight adversarial strategies an operator might use to hide, only extreme variation of the work