LATIDIA · Ciberseguridad
ExclaveFL: Afirmaciones verificables para el aprendizaje federado mediante exclaves
arXiv:2412.10537v5 Tipo de anuncio: sustitución Resumen: En el aprendizaje federado (FL), los proveedores de datos entrenan conjuntamente un modelo de aprendizaje automático sin compartir los datos de entrenamiento. Esto dificulta la presentación de afirmaciones verificables.
WhatsApp ↗Telegram ↗
La noticia
arXiv:2412.10537v5 Announce Type: replace Abstract: In federated learning (FL), data providers jointly train a machine learning model without sharing training data. This makes it challenging to provide verifiable claims about the trained model, e.g., related to the employed training data, data sanitization, or training algorithm---a malicious data provider can simply deviate from the correct training protocol without detection. Prior FL training systems have used trusted execution environments (TEEs) to protect the training computation, relying on the confidentiality and integrity of TEEs. TEE confidentiality, however, has been shown to be vulnerable to various attacks, e.g., via side channels. We describe ExclaveFL, a system for training FL models that establishes verifiable claims