VGIA certifies exact recovery of individual records from aggregated gradients in federated learning using a subspace verification test on ReLU hyperplanes.
1322–1333
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
VFEFL introduces a CC-DVFE scheme and robust aggregation to achieve privacy-preserving federated learning with malicious client detection without dual-server or trusted-party assumptions.
citing papers explorer
-
No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learning
VGIA certifies exact recovery of individual records from aggregated gradients in federated learning using a subspace verification test on ReLU hyperplanes.
-
VFEFL: Privacy-Preserving Federated Learning against Malicious Clients via Verifiable Functional Encryption
VFEFL introduces a CC-DVFE scheme and robust aggregation to achieve privacy-preserving federated learning with malicious client detection without dual-server or trusted-party assumptions.