LATIDIA · Ciberseguridad

Hacia la verificación de las redes neuronales contra las perturbaciones de volteo de bits multiparámetro

arXiv:2610.08876v1 Tipo de anuncio: nuevo Resumen: Las fallas de hardware pueden voltear bits en los pesos almacenados de una red neuronal cuantificada, lo que podría comprometer sus predicciones. Si bien tales fallas suelen afectar a múltiples par

La noticia

arXiv:2610.08876v1 Announce Type: new Abstract: Hardware faults can flip bits in the stored weights of a quantized neural network, potentially compromising its predictions. While such faults typically affect multiple parameters simultaneously, existing verifiers are limited to single-parameter perturbations due to the combinatorial explosion of possible flip locations in large networks. We present mBFV (m-BitFlip Verifier), an efficient verification framework that proves robustness against simultaneous bit flips across multiple parameters without explicitly enumerating these combinations. mBFV achieves this via a novel multi-parameter bound propagation technique that directly aggregates the m worst-case contributions. To further tighten these bounds, mBFV employs a branch-and-bound mechanism over perturbation locations, partitioning the potential flips to smaller