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.
A review on graph neural network methods in financial applications
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Relational Probing replaces the LM output head with a trainable relation head that induces graphs from hidden states and optimizes them end-to-end for stock trend prediction, showing gains over co-occurrence baselines.
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.
-
Relational Probing: LM-to-Graph Adaptation for Financial Prediction
Relational Probing replaces the LM output head with a trainable relation head that induces graphs from hidden states and optimizes them end-to-end for stock trend prediction, showing gains over co-occurrence baselines.