An empirical study showing that graph prompt learning exposes node attributes and links to inference attacks, with prompt tuning adding little extra risk over frozen GNN baselines.
Relevance-aware anomalous users detection in social network via graph neural network,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning
An empirical study showing that graph prompt learning exposes node attributes and links to inference attacks, with prompt tuning adding little extra risk over frozen GNN baselines.