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.
The core idea is to construct a smoothed classifier by randomly dropping edges and ag- gregating predictions over multiple randomized graph in- stances
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.