A malicious client in federated graph learning can infer which client owns a node by combining gradient eavesdropping, graph reconstruction, and class-prototype matching.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks
A malicious client in federated graph learning can infer which client owns a node by combining gradient eavesdropping, graph reconstruction, and class-prototype matching.