LATIDIA · Ciberseguridad

Aegis: Enmascaramiento de gradiente generativo para el aprendizaje federado médico que preserva la privacidad

arXiv: 2609.38339v1Tipo de anuncio: nuevo Resumen: El aprendizaje federado (FL) se ha convertido en un paradigma fundamental para la IA médica multiinstitucional, lo que permite a los hospitales y centros de investigación formar conjuntamente modelos de diagnóstico con

La noticia

arXiv:2609.38339v1 Announce Type: new Abstract: Federated learning (FL) has become a foundational paradigm for multi-institutional medical AI, allowing hospitals and research centers to jointly train diagnostic models without exchanging patient records. This privacy promise, however, is increasingly contested: a malicious or honest-but-curious server can launch model inversion attacks (MIAs) that reconstruct private patient images directly from shared model updates, and recent scalable, closed-form attacks penetrate even secure aggregation at clinically realistic batch sizes. Existing defenses face an unsatisfactory dilemma. Gradient-perturbation methods such as differential privacy and pruning trade away the diagnostic accuracy on which clinical reliability depends, while cryptographic protocols add system complexity yet still leave updates exposed to these