Jellyfish enables zero-shot federated unlearning through synthetic proxy data generation, channel-restricted knowledge disentanglement, and a composite loss with repair to forget target data while retaining model utility.
arXiv preprint arXiv:2201.00763 (2022)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Trigger color significantly affects semantic backdoor attack success in federated learning on CelebA hair-color classification, with white triggers better for blond targets and black for black targets.
citing papers explorer
-
Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement
Jellyfish enables zero-shot federated unlearning through synthetic proxy data generation, channel-restricted knowledge disentanglement, and a composite loss with repair to forget target data while retaining model utility.
-
Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks
Trigger color significantly affects semantic backdoor attack success in federated learning on CelebA hair-color classification, with white triggers better for blond targets and black for black targets.