GRL-Safety benchmark shows that safety in graph representation learning depends on interactions between method design and specific graph stresses rather than broad method families.
Hamilton, Rex Ying, and Jure Leskovec
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Prism defines a duality defect δ(L,P) to measure structural symmetry deviation in graphs and reports it detects rising stress in S&P 500 networks before correlation spikes appear.
A two-stage GNN-plus-ModernBERT framework detects social engineering attacks in email networks by first filtering structural anomalies at 86% recall and then verifying content to reach over 92% precision on augmented Enron data.
citing papers explorer
-
On the Safety of Graph Representation Learning
GRL-Safety benchmark shows that safety in graph representation learning depends on interactions between method design and specific graph stresses rather than broad method families.
-
Prism: Structural Symmetry Scanning via Duality-Constrained Laplacian Projection
Prism defines a duality defect δ(L,P) to measure structural symmetry deviation in graphs and reports it detects rising stress in S&P 500 networks before correlation spikes appear.
-
Filter-then-Verify: A Multiphase GNN and ModernBERT Framework for Social Engineering Detection in Email Networks
A two-stage GNN-plus-ModernBERT framework detects social engineering attacks in email networks by first filtering structural anomalies at 86% recall and then verifying content to reach over 92% precision on augmented Enron data.