Recovering Private Text in Federated Learning of Language Models. (arXiv:2205.08514v1 [cs.CL])

Federated learning allows distributed users to collaboratively train a model
while keeping each user's data private. Recently, a growing body of work has
demonstrated that an eavesdropping attacker can effectively recover image data
from gradients transmitted during federated learning. However, little progress
has been made in recovering text data. In this paper, we present a novel attack
method FILM for federated learning of language models -- for the first time, we
show the feasibility of recovering text from large batch …

language text