PRAETORIAN defends GNNs from backdoors by spotting large or highly influential trigger structures, cutting attack success to 0.55% with only 0.62% clean accuracy loss.
Robust graph convolutional networks against adversarial attacks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
PRAETORIAN defends GNNs from backdoors by spotting large or highly influential trigger structures, cutting attack success to 0.55% with only 0.62% clean accuracy loss.