GBFA shows GNNs can be degraded by flipping one or a few weight bits in a targeted layer, though the advantage over random flips is marginal at the reported minimum bit error rates.
Global explanation supervision for graph neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Bit-Flip Fault Attack: Crushing Graph Neural Networks via Gradual Bit Search
GBFA shows GNNs can be degraded by flipping one or a few weight bits in a targeted layer, though the advantage over random flips is marginal at the reported minimum bit error rates.