LATIDIA · Ciberseguridad
Análisis de la unidad de carga/almacenamiento de la GPU y exposición de sus riesgos de seguridad
arXiv:2611.23022v1 Tipo de anuncio: cruzado Resumen: Las GPU son la principal plataforma para el aprendizaje automático a gran escala y dan potencia a los superordenadores más grandes. Sus unidades de carga/almacenamiento (LSU) suelen determinar el rendimiento del núcleo y tienen
WhatsApp ↗Telegram ↗
La noticia
arXiv:2611.23022v1 Announce Type: cross Abstract: GPUs are the main platform for large-scale machine learning and power the largest supercomputers. Their load/store units (LSUs) often determine kernel performance and have been exploited in prior attacks. Yet what is known about the LSU is only a few isolated mechanisms and parameters, and even a single one has been enough for an attack. In particular, it is still unknown what a load costs, where loads contend, and even whether a warp can starve due to contention. Until each is measured, neither its security risk nor a defense is known. We reverse-engineer how the LSU serves load instructions on recent NVIDIA GPUs with microbenchmarks