LATIDIA · Ciberseguridad

TensorBound: Caracterización de fallos de enlace de tensores en pilas de compiladores y de tiempo de ejecución de IA

arXiv:2610.37838v1 Anuncio Tipo: nuevo Resumen: Las pilas de compilación y tiempo de ejecución de IA deben preservar los vínculos entre los valores de los tensores y sus operaciones, almacenamiento y estado de ejecución. Estos vínculos pueden fallar mientras que el subyacente

La noticia

arXiv:2610.37838v1 Announce Type: new Abstract: AI compiler and runtime stacks must preserve bindings between tensor values and their operations, storage, and execution state. These bindings can fail while the underlying objects remain present, with symptoms appearing in another layer. We present TensorBound, an empirical study of tensor binding failures in IREE and the XLA and PyTorch ecosystems. The study analyzes 264 reports and reconstructs 149 distinct repaired causes through source tracing and comparisons of pre-fix and repaired revisions. Each reconstruction connects the first invalid decision to its violated condition, physical effect, and repair. Missing eligibility checks, incorrect mappings or translations, and lost or omitted relations account for 69.1% of repaired