LATIDIA · Ciberseguridad

Alineación normal: recuperación mejorada de signos criptoanalíticos en redes de etiqueta dura

arXiv:2609.18751v1 Tipo de anuncio: nuevo Resumen: En EUROCRYPT 2025, Carlini et al. propusieron un avance en la extracción criptoanalítica en redes neuronales profundas (DNN) de etiqueta dura (S1), demostrando un signo de tiempo polinómico

La noticia

arXiv:2609.18751v1 Announce Type: new Abstract: At EUROCRYPT 2025, Carlini et al. proposed a breakthrough in the cryptanalytic extraction on hard-label (S1) deep neural networks (DNNs), demonstrating polynomial-time signature and sign recovery. However, Carlini et al.'s sign-recovery method (which we call Future Toggle) suffers only a marginal advantage over random guessing, producing high-confidence wrong sign predictions in deeper layers. Such errors trigger expensive exponential-time enumeration. This work presents Normal Alignment, a novel statistical sign-recovery approach for S1 DNNs. Drawing on the expected length difference between projected normals of adjacent decision facets at dual points, our method infers neuron signs via normal-signature alignment. It delivers higher voting accuracy and pushes erroneous predictions