CP-GBA distills a queryable repository of promptable subgraph triggers via graph prompt learning to achieve transferable backdoor attacks on GNNs with state-of-the-art success rates across paradigms and defenses.
Graph neural backdoor: Fundamentals, methodologies, applications, and future directions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2verdicts
UNVERDICTED 2representative citing papers
GRAFT introduces graphlet-based triggers for backdoor attacks on GNN hardware security systems, achieving up to 100% attack success rate on ISCAS-85 and TrustHub benchmarks while preserving circuit functionality.
citing papers explorer
-
Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers
CP-GBA distills a queryable repository of promptable subgraph triggers via graph prompt learning to achieve transferable backdoor attacks on GNNs with state-of-the-art success rates across paradigms and defenses.
-
GRAFT: Graphlet-Triggered Backdoor Attack on GNN-Based Hardware Security Systems
GRAFT introduces graphlet-based triggers for backdoor attacks on GNN hardware security systems, achieving up to 100% attack success rate on ISCAS-85 and TrustHub benchmarks while preserving circuit functionality.