LATIDIA · Ciberseguridad

LightSplit: Aprendizaje dividido práctico que preserva la privacidad a través de proyecciones ortogonales (versión completa)

arXiv:2605.13265v2 Announce Type: cross Resumen: Split learning (SL) permite el entrenamiento colaborativo mediante la partición de una red neuronal entre clientes y un servidor central. Sin embargo, la interfaz de capa de corte introduce una clave

La noticia

arXiv:2605.13265v2 Announce Type: cross Abstract: Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server. However, the cut-layer interface introduces a key challenge: high-dimensional activations incur substantial communication overhead while exposing representations vulnerable to reconstruction attacks. Existing approaches typically address efficiency or privacy in isolation. We propose LightSplit, which limits information exposure and reduces communication overhead via a lightweight fixed orthogonal random projection at the cut layer. Based on Shannon's information theory, this projection acts as an information bottleneck that restricts instance-specific information and suppresses exploitable per-sample signals. With low-dimensional projections sent instead of raw activations, the server operates on lifted representations without