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.
Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, and Marion Neumann
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
GraphVec produces transferable fixed-dimensional graph embeddings via spectral features from multi-scale global graphs and a convergent mean-alignment procedure, outperforming baselines on cross-domain few-shot classification and clustering across 13 datasets.
ALL-IN projects node features to a random shared space and uses covariance operators to produce representations invariant to input feature permutations and orthogonal transformations, enabling transfer across graph datasets.
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.
-
GraphVec: Cross-Domain Graph Vectorization for Graph-Level Representation Learning
GraphVec produces transferable fixed-dimensional graph embeddings via spectral features from multi-scale global graphs and a convergent mean-alignment procedure, outperforming baselines on cross-domain few-shot classification and clustering across 13 datasets.
-
Bridging Input Feature Spaces Towards Graph Foundation Models
ALL-IN projects node features to a random shared space and uses covariance operators to produce representations invariant to input feature permutations and orthogonal transformations, enabling transfer across graph datasets.