OPFL: Optimistic Verification of Federated Learning via Empirical Boundary
OPFL verifies federated learning inside MPC with an empirical gradient boundary, stopping model poisoning at much lower cost.
1 stories, newest first · one card per story
OPFL verifies federated learning inside MPC with an empirical gradient boundary, stopping model poisoning at much lower cost.
Today 528 readers · 614 views · 478 reads · all time 158K views