LATIDIA · Ciberseguridad

Selle, luego muestree: Pruebas por capas muestreadas para inferencia LLM verificable de GPT-2 a 70B

arXiv: 2609.27367v1Tipo de anuncio: nuevo Resumen: La verificación de la inferencia del modelo de lenguaje subcontratado requiere un cálculo identificado con precisión y una auditoría cuyo costo un servicio puede pagar. Presentamos pruebas por capas muestreadas

La noticia

arXiv:2609.27367v1 Announce Type: new Abstract: Verifying outsourced language-model inference requires a precisely identified computation and an audit whose cost a service can afford. We present Sampled Layerwise Proofs (SLP), a protocol and prototype that commits the boundary activations of every chunk of an inference trace, absorbs all commitments before any challenge is drawn, and then proves a verifier-selected subset of chunks together with the chunks that bind the prompt and the answer. Audit coverage becomes a runtime parameter over one set of commitments: on a TinyLlama-1.1B trace, proving seven of 47 chunks takes 22.0% of the time and 6.8% of the proof size of proving all 47. Because proof cost