LATIDIA · Ciberseguridad

CertMoE: Certificación de robustez para LLM de mezcla de expertos a través de suavizado consciente de enrutamiento

arXiv: 2610.29395v1Tipo de anuncio: nuevo Resumen: La robustez demostrable es una piedra angular del aprendizaje automático confiable, con el objetivo de garantizar las predicciones del modelo bajo perturbaciones adversas. Marco de certificación existentewor

La noticia

arXiv:2610.29395v1 Announce Type: new Abstract: Provable robustness is a cornerstone of trustworthy machine learning, aiming to guarantee model predictions under adversarial perturbations. Existing certification frameworks, inspired by abstract interpretation or symbolic execution, typically assume a fixed computation graph, where input perturbations or variations affect only model outputs but not the underlying execution path. This assumption, however, is violated in Mixture-of-Experts (MoE) Large Language Models (LLMs), whose input-dependent routing induces discrete and dynamic execution paths. Crucially, this dynamic computation changes the certified object from a single fixed function to a composition of input-dependent sub-functions, leading to unreliable certification guarantees. This paper presents \textsc{CertMoE}, the first routing-aware robustness certification framework for MoE