GDBR reconstructs batch label counts from a single shared non-output layer's gradient by propagating gradients to the logits using auxiliary data estimates.
Revealing and protecting labels in distributed training,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning
GDBR reconstructs batch label counts from a single shared non-output layer's gradient by propagating gradients to the logits using auxiliary data estimates.