LATIDIA · Ciberseguridad

OptiPrime: Optimización de la inferencia privada a través del codiseño de protocolos y hardware

arXiv:2609.16898v1 Tipo de anuncio: cross Resumen: La inferencia de la red neuronal profunda privada (DNN) basada en el cifrado homomórfico híbrido (HE) y la computación multipartita (MPC) puede proteger los datos del usuario con una garantía formal, b

La noticia

arXiv:2609.16898v1 Announce Type: cross Abstract: Private deep neural network (DNN) inference based on hybrid homomorphic encryption (HE) and multi-party computation (MPC) can protect user data with a formal guarantee, but at the cost of significant latency overhead due to HE. Customized HE accelerators have been proposed and have achieved orders-of-magnitude speedup for individual HE operations. However, when directly applying a commercial HE accelerator to state-of-the-art HE-MPC frameworks, we observe only limited end-to-end performance gain. This is because HE-MPC frameworks often require wireless transmission of input and output ciphertexts for each HE operation, leading to a severe network communication bottleneck. To overcome this challenge, we introduce OptiPrime, a protocol-hardware co-optimization framework