LATIDIA · Ciberseguridad

Extracción de modelo criptoanalítico de etiqueta dura de extremo a extremo mediante recuperación eficiente de signos

arXiv:2609.21941v1 Tipo de anuncio: nuevo Resumen: La importancia de las redes neuronales profundas (DNN) es ampliamente reconocida, y los parámetros obtenidos a través de la capacitación se consideran activos valiosos. Recientemente, los ataques que ext

La noticia

arXiv:2609.21941v1 Announce Type: new Abstract: The importance of deep neural networks (DNNs) is widely recognized, and the parameters obtained through training are regarded as valuable assets. Recently, attacks that extract these parameters using only oracle queries to a DNN have been actively studied at IACR conferences. The hard-label setting is the most challenging setting for model extraction, where an adversary can observe only the final output label, such as "dog" or "cat." At Eurocrypt 2025, Carlini et al. proposed polynomial-time hard-label extraction of ReLU-based MLPs. However, one step of this attack process, i.e., sign recovery, requires a large number of queries and substantial computation. Implementing this step in a black-box