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.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across transverse-momentum regimes.
BrainSimSiam applies positive-only Siamese self-supervised learning to fMRI data to produce representations that generalize across downstream tasks and outperform supervised baselines.
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.
-
Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane
Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across transverse-momentum regimes.
-
Learning Robust and Task-Invariant Functional Representation from fMRI through Siamese Self-Supervised Learning
BrainSimSiam applies positive-only Siamese self-supervised learning to fMRI data to produce representations that generalize across downstream tasks and outperform supervised baselines.