DRAGD and DRAGDP reconstruct erased federated-learning images by sequentially matching post-unlearning and pre-unlearning gradients, with DRAGDP adding a public-image prior.
Part" subset, corresponding to the retained gradients, while the gradients of the remaining 12 images were forgotten. As the reconstruction progresses, it is observed that the
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
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences
DRAGD and DRAGDP reconstruct erased federated-learning images by sequentially matching post-unlearning and pre-unlearning gradients, with DRAGDP adding a public-image prior.