A defense framework detects both subgraph and feature-based graph backdoors by exploiting their lower node-neighborhood feature homophily via neighbor-aware reconstruction loss and robust training.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Inductive subgraphs serve as shortcuts in heterophilic graphs, and CD-GNN disentangles spurious from causal subgraphs by blocking non-causal paths to improve robustness and accuracy.
citing papers explorer
-
Universal Graph Backdoor Defense: A Feature-based Homophily Perspective
A defense framework detects both subgraph and feature-based graph backdoors by exploiting their lower node-neighborhood feature homophily via neighbor-aware reconstruction loss and robust training.
-
Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
Inductive subgraphs serve as shortcuts in heterophilic graphs, and CD-GNN disentangles spurious from causal subgraphs by blocking non-causal paths to improve robustness and accuracy.