Bit-flip attacks can degrade GNN expressivity with far fewer bit flips than previously analyzed, especially for ReLU-activated GNNs on homophilous graphs with low-dimensional or one-hot features.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Relationship Between Robustness and Expressivity of Graph Neural Networks
Bit-flip attacks can degrade GNN expressivity with far fewer bit flips than previously analyzed, especially for ReLU-activated GNNs on homophilous graphs with low-dimensional or one-hot features.