ShadowMerge exploits relation-channel conflicts to poison graph-based agent memory, achieving 93.8% average attack success rate on Mem0 and real-world datasets while bypassing existing defenses.
Backdoor attacks to graph neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
dataset 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2representative citing papers
PRAETORIAN reduces GNN backdoor attack success rate to 0.55% with 0.62% clean accuracy drop by targeting the need for many or highly influential trigger nodes.
citing papers explorer
-
ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
ShadowMerge exploits relation-channel conflicts to poison graph-based agent memory, achieving 93.8% average attack success rate on Mem0 and real-world datasets while bypassing existing defenses.
-
Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
PRAETORIAN reduces GNN backdoor attack success rate to 0.55% with 0.62% clean accuracy drop by targeting the need for many or highly influential trigger nodes.