LATIDIA · Ciberseguridad
BlockJack: ataques de fallo de redireccionamiento entre inquilinos a la traducción de direcciones de la caché KV paginada en el servicio de LLM
arXiv:2611.25945v1 Tipo de anuncio: nuevo Resumen: Los «frameworks» de servicio de modelos de lenguaje grandes (LLM) aceleran la inferencia al conservar los estados calculados previamente en una caché de clave-valor (KV). Los marcos de servicio paginados, como vLLM,
WhatsApp ↗Telegram ↗
La noticia
arXiv:2611.25945v1 Announce Type: new Abstract: Large language model (LLM) serving frameworks accelerate inference by retaining previously computed states in a key-value (KV) cache. Paged serving frameworks such as vLLM organize this cache through block tables analogous to OS page tables, which map each request's logical KV blocks to physical KV blocks, forming a software-managed address translation layer. Although fault attacks such as Rowhammer have exploited OS page tables to redirect memory accesses, prior fault attacks on LLMs have largely targeted the data plane, i.e., model weights or KV-cache contents, leaving KV-cache mapping unexplored. We present BlockJack (i.e., Block Hijack), the first KV cache address-translation fault attack in LLM inference. By