GRID adds crafted noise to prediction vectors of selected core nodes so linked node pairs look like n-hop unlinked pairs, while preserving predicted labels.
Extracting training data from large language models
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
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models
GRID adds crafted noise to prediction vectors of selected core nodes so linked node pairs look like n-hop unlinked pairs, while preserving predicted labels.