LATIDIA · Ciberseguridad

Extracción criptoanalítica algebraica en redes neuronales de etiqueta dura

arXiv: 2608.05736v2Tipo de Anuncio: reemplazar Resumen: Aunque el ataque de extracción de modelos de última generación en la Red Neuronal Totalmente Conectada (FCN) de etiqueta dura por Carlini et al. en EUROCRYPT 2025 tiene tiempo polinomial com

La noticia

arXiv:2608.05736v2 Announce Type: replace Abstract: Although the state-of-the-art model extraction attack on the hard-label Fully-connected Neural Network (FCN) by Carlini et al. at EUROCRYPT 2025 has polynomial-time complexity in theory, its dual-point clustering relies on singular value decomposition (SVD) with a time complexity of $\mathcal{O}(n^2 (d^{(k)})^3)$, resulting in huge runtime in practice. To address this computational bottleneck, this work transforms Carlini et al.'s geometric-view hard-label attack into an algebraic framework, and proposes two efficient clustering methods: Normal Rank Check (NRC) and Approximate Signature Vector (ASV). The NRC and ASV methods replace Carlini et al.'s heavy SVD-based rank checking with simple rank checking or inner-product operations, reducing the clustering complexity to