The paper demonstrates a black-box model extraction attack on graph classification models that leverages binary subgraph explanations to guide Monte Carlo edge sensitivity estimation with concentration guarantees.
Computing graph edit distance via neural graph matching
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A graph-based ECO method for XLS HLS uses GED to detect IR changes, generates constraint-preserving patches, and maintains original schedules with high reuse and full correctness in experiments.
citing papers explorer
-
Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?
The paper demonstrates a black-box model extraction attack on graph classification models that leverages binary subgraph explanations to guide Monte Carlo edge sensitivity estimation with concentration guarantees.
-
Graph-Based ECO and Patch Generation for High-Level Synthesis
A graph-based ECO method for XLS HLS uses GED to detect IR changes, generates constraint-preserving patches, and maintains original schedules with high reuse and full correctness in experiments.