BadImplant is the first multi-targeted backdoor attack on GNN graph classification that uses subgraph injection to achieve high success rates on multiple target labels with minimal clean accuracy loss.
Security and privacy issues in deep learning: a brief review,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BadImplant: Injection-based Multi-Targeted Graph Backdoor Attack
BadImplant is the first multi-targeted backdoor attack on GNN graph classification that uses subgraph injection to achieve high success rates on multiple target labels with minimal clean accuracy loss.