GOOD-MIA combines invariant risk minimization, a graph information bottleneck, and risk extrapolation to run membership inference attacks against graph neural networks across different data domains.
Out-of-distribution generalization via risk extrapolation (rex)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
An Out-Of-Distribution Membership Inference Attack Approach for Cross-Domain Graph Attacks
GOOD-MIA combines invariant risk minimization, a graph information bottleneck, and risk extrapolation to run membership inference attacks against graph neural networks across different data domains.