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.
Adversarial perturbations are absorbed into the variances of these distributions, thereby reducing their im- pact on the learned representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.