LATIDIA · Ciberseguridad

Canales de puerta trasera ocultos en el espacio latente: extender la indetectabilidad criptográfica a las redes neuronales modernas

arXiv:2605.13214v4 Tipo de anuncio: reemplazar Resumen: Los resultados criptográficos recientes establecen que las redes neuronales pueden ser backdoored de tal manera que ningún algoritmo eficiente puede distinguirlas de un modelo limpio. Estas garantías

La noticia

arXiv:2605.13214v4 Announce Type: replace Abstract: Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited practical relevance, leaving open whether comparable undetectability extends to modern, end-to-end trained networks. We construct such an attack mechanism for deep neural network architectures, closely aligned to the cryptographic notion of undetectability, by identifying backdoor channels as learned latent directions, and show that the question of undetectability reduces to a hypothesis test between two unknown distributions over model parameters, which we conjecture to be intractable in practice. The consequence of this reframing