SwitchNet: protecting neural networks by structure obfuscation and switch-controlled inference
Artículo
Acceso abierto
Artículo
DOAJ
Abstract Training deep learning models requires substantial financial and human resources, so once deployed in untrusted environments, these models immediately attract the attention of attackers who seek to steal and mis...
LCC TENDOkNvbXB1dGVyIGVuZ2luZWVyaW5nLiBDb21wdXRlciBoYXJkd2FyZQ~~; LCC:Electronic computers. Computer scienceIdioma eng
Acceso abiertoRuta libre sin proxy. Acceso recomendado cuando no hay suscripción activa.
Open Access