SaFL: Sybil-aware Federated Learning with Application to Face Recognition. (arXiv:2311.04346v1 [cs.CV])

Federated Learning (FL) is a machine learning paradigm to conduct
collaborative learning among clients on a joint model. The primary goal is to
share clients' local training parameters with an integrating server while
preserving their privacy. This method permits to exploit the potential of
massive mobile users' data for the benefit of machine learning models'
performance while keeping sensitive data on local devices. On the downside, FL
raises security and privacy concerns that have just started to be studied. To …

application aware clients data exploit face recognition federated federated learning local machine machine learning mobile paradigm privacy recognition server share training