LATIDIA · Ciberseguridad

AutoPoly-HE: Diseño autónomo de activaciones polinómicas para la inferencia cifrada de preservación de la privacidad

arXiv: 2610.19325v1Tipo de anuncio: nuevo Resumen: El aprendizaje automático que preserva la privacidad se ha vuelto fundamental para implementar la inteligencia artificial en dominios sensibles como la atención médica, las finanzas y el monitoreo de infraestructura en

La noticia

arXiv:2610.19325v1 Announce Type: new Abstract: Privacy-preserving machine learning has become critical for deploying artificial intelligence in sensitive domains such as healthcare, finance, and infrastructure monitoring. Homomorphic encryption (HE) enables secure inference on encrypted data. Despite its advantages, HE is not compatible with nonlinear activation functions found in machine learning models. Existing methods mitigate this problem by manually designing polynomial approximations for these activation functions. However, these functions do not account for the differences in dataset characteristics or model architecture. Furthermore, these functions are also limited to the accuracies of convolutional neural network (CNN) models. In this work, we propose an autonomous framework that selects polynomial activation functions tailored to each