A query-based graph injection attack that selects edges from the victim's neighborhood and generates node features with a Bayesian search, outperforming prior attacks on six datasets while preserving homophily.
Revisiting graph adversarial attack and defense from a data distribution perspective
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Query-Based and Unnoticeable Graph Injection Attack from Neighborhood Perspective
A query-based graph injection attack that selects edges from the victim's neighborhood and generates node features with a Bayesian search, outperforming prior attacks on six datasets while preserving homophily.