LATIDIA · Ciberseguridad

Implementación de una puerta trasera indetectable de caja blanca para funciones aleatorias de Fourier

arXiv:2609.16403v1 Tipo de anuncio: nuevo Resumen: Goldwasser et al. mostraron que las puertas traseras indetectables se pueden plantar en modelos de aprendizaje automático entrenados con el algoritmo Random Fourier Features (RFF), bajo una dureza como

La noticia

arXiv:2609.16403v1 Announce Type: new Abstract: Goldwasser et al. showed that undetectable backdoors can be planted in machine learning models trained with the Random Fourier Features (RFF) algorithm, under a hardness assumption tied to the Continuous Learning With Errors (CLWE) problem. Under standard cryptographic assumptions, even a full white-box audit of a model's weights cannot detect this class of backdoor. The construction is stated in terms of cryptographic reductions and probabilistic lemmas, without a reference implementation, and relies on secondary machinery such as the Sparse Gaussian Pancakes distribution and a homogeneous CLWE conditional density. Its realizability in ordinary numerical code is not obvious from the paper alone. This paper implements the