GraphIP-Bench is a new unified benchmark showing GNN model extraction succeeds at moderate query budgets while most defenses fail to prevent it or retain verification signals on surrogates.
A survey on model extraction attacks and defenses for large language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
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.
World models enable efficient AI planning but create risks from adversarial corruption, goal misgeneralization, and human bias, demonstrated via attacks that amplify errors and reduce rewards on models like RSSM and DreamerV3.
A maximum mean discrepancy detector on semantic query embeddings achieves 0.3% benign FPR and 90.5% average TPR for model extraction detection in LLM API traffic when calibrated only on benign data.
citing papers explorer
-
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
GraphIP-Bench is a new unified benchmark showing GNN model extraction succeeds at moderate query budgets while most defenses fail to prevent it or retain verification signals on surrogates.
-
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.
-
Safety, Security, and Cognitive Risks in World Models
World models enable efficient AI planning but create risks from adversarial corruption, goal misgeneralization, and human bias, demonstrated via attacks that amplify errors and reduce rewards on models like RSSM and DreamerV3.
-
An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic
A maximum mean discrepancy detector on semantic query embeddings achieves 0.3% benign FPR and 90.5% average TPR for model extraction detection in LLM API traffic when calibrated only on benign data.