BA-Logic enables high-success clean-label backdoor attacks on GNNs by coordinating a poisoned node selector and a logic-poisoning trigger generator to alter internal prediction decisions.
From the table, we obtain the following key observations: •The adaptive defense can partially weaken the backdoor, indicating promising directions against logic poisoning
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
-
Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks
BA-Logic enables high-success clean-label backdoor attacks on GNNs by coordinating a poisoned node selector and a logic-poisoning trigger generator to alter internal prediction decisions.