LATIDIA · Ciberseguridad

Minas terrestres de enfriamiento: ataques de interferencia entre inquilinos en puertas de enlace de LLM

arXiv: 2610.05089v1Tipo de anuncio: nuevo Resumen: las puertas de enlace LLM aplican cuotas de inquilinos separadas mientras comparten implementaciones de modelos y registros de enfriamiento que excluyen temporalmente los backends defectuosos. Sin embargo, la solicitud de un inquilino falla

La noticia

arXiv:2610.05089v1 Announce Type: new Abstract: LLM gateways enforce separate tenant quotas while sharing model deployments and cooldown records that temporarily exclude failing backends. However, a tenant's request failure can update these shared records and restrict other tenants' access to serviceable deployments. We identify two attacks that exploit this gap in LiteLLM. The first uses requests rejected at the key's requests-per-minute (RPM) limit: caller-supplied identifiers for known registered deployments reach failure handling, allowing two rejected requests to redirect another tenant to fallback with zero upstream calls from those requests. The second uses admitted traffic to create cooldown records that persist after backend capacity recovers. To address these failures, we design an