LATIDIA · Ciberseguridad

Caracterización de la separabilidad estadística en TP-CRIV para modelos de IA probabilística

arXiv:2610.11163v1 Tipo de anuncio: nuevo Resumen: La verificación de identidad de desafío-respuesta de terceros (TP-CRIV) permite a un verificador independiente evaluar si un reclamante posee un modelo idéntico a un despliegue remoto

La noticia

arXiv:2610.11163v1 Announce Type: new Abstract: Third-party challenge-response identity verification (TP-CRIV) enables an independent verifier to assess whether a claimant possesses a model identical to a remotely deployed model without directly accessing the reference model. However, for probabilistic AI models, repeated executions of the same query may produce different outputs and therefore different verification observations. This raises the question of how such stochastic evidence should be accumulated and how much evidence is required for reliable verification. In this work, we characterize statistical separability in TP-CRIV of probabilistic AI models. Specifically, we relate challenge-wise behavior of matching and non-matching provers to verification-level separability. The characterization explicitly describes how the numbers of independent