Imagen de Portada

How Explanations Leak the Decision Logic: Stealing Graph Neural Networks via Explanation Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ma, Bin, Feng, Yuyuan, Lin, Minhua, Dai, Enyan
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep Intellectual Property Protection
por: Dai, Enyan, et al.
Publicado: (2024)

Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks
por: Zhang, Yuxiang, et al.
Publicado: (2026)

SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning
por: Zhang, Yuxiang, et al.
Publicado: (2026)

Stealing Training Graphs from Graph Neural Networks
por: Lin, Minhua, et al.
Publicado: (2024)

LiSA: Leveraging Link Recommender to Attack Graph Neural Networks via Subgraph Injection
por: Zhang, Wenlun, et al.
Publicado: (2025)

Backdoor or Manipulation? Graph Mixture of Experts Can Defend Against Various Graph Adversarial Attacks
por: Feng, Yuyuan, et al.
Publicado: (2025)

General Protein Pretraining or Domain-Specific Designs? Benchmarking Protein Modeling on Realistic Applications
por: Yan, Shuo, et al.
Publicado: (2025)

Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks
por: Zhang, Jiaxing, et al.
Publicado: (2025)

Graph Neural Network Causal Explanation via Neural Causal Models
por: Behnam, Arman, et al.
Publicado: (2024)

The GECo algorithm for Graph Neural Networks Explanation
por: Calderaro, Salvatore, et al.
Publicado: (2024)

Game-theoretic Counterfactual Explanation for Graph Neural Networks
por: Chhablani, Chirag, et al.
Publicado: (2024)

GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
por: Zhao, Kaixiang, et al.
Publicado: (2026)

Neural Networks Decoded: Targeted and Robust Analysis of Neural Network Decisions via Causal Explanations and Reasoning
por: Diallo, Alec F., et al.
Publicado: (2024)

Explanations are a Means to an End: Decision Theoretic Explanation Evaluation
por: Guo, Ziyang, et al.
Publicado: (2025)

GRExplainer: A Universal Explanation Method for Temporal Graph Neural Networks
por: Li, Xuyan, et al.
Publicado: (2025)

Extending Decision Predicate Graphs for Comprehensive Explanation of Isolation Forest
por: Ceschin, Matteo, et al.
Publicado: (2025)

MEGAN: Multi-Explanation Graph Attention Network
por: Teufel, Jonas, et al.
Publicado: (2022)

Comparative Explanations: Explanation Guided Decision Making for Human-in-the-Loop Preference Selection
por: Chakraborty, Tanmay, et al.
Publicado: (2025)

GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks
por: Wang, Xiaoqi, et al.
Publicado: (2022)

Pathwise Explanation of ReLU Neural Networks
por: Lim, Seongwoo, et al.
Publicado: (2025)

Regularizing Explanations in Bayesian Convolutional Neural Networks
por: Bekkemoen, Yanzhe, et al.
Publicado: (2021)

Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
por: Downer, Jane, et al.
Publicado: (2024)

Graph Neural Networks based Log Anomaly Detection and Explanation
por: Li, Zhong, et al.
Publicado: (2023)

MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation
por: Yu, Zhaoning, et al.
Publicado: (2024)

Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studies
por: Teufel, Jonas, et al.
Publicado: (2023)

ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks
por: Zhang, Yu, et al.
Publicado: (2026)

Uncertainty Quantification for Gradient-based Explanations in Neural Networks
por: Mulye, Mihir, et al.
Publicado: (2024)

FAME: Formal Abstract Minimal Explanation for Neural Networks
por: Boumazouza, Ryma, et al.
Publicado: (2026)

Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?
por: Nimase, Ojas, et al.
Publicado: (2026)

Counterfactual Explanations for Hypergraph Neural Networks
por: Veglianti, Fabiano, et al.
Publicado: (2026)

Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation
por: Jiang, Junqi, et al.
Publicado: (2023)

Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
por: Chen, Yanda, et al.
Publicado: (2024)

Obtaining Example-Based Explanations from Deep Neural Networks
por: Dong, Genghua, et al.
Publicado: (2025)

Attribution Explanations for Deep Neural Networks: A Theoretical Perspective
por: Deng, Huiqi, et al.
Publicado: (2025)

A Model of Causal Explanation on Neural Networks for Tabular Data
por: Isozaki, Takashi, et al.
Publicado: (2025)

RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
por: Zhang, Jiaxing, et al.
Publicado: (2023)

Rule2Text: Natural Language Explanation of Logical Rules in Knowledge Graphs
por: Shirvani-Mahdavi, Nasim, et al.
Publicado: (2025)

Improving the Validity of Decision Trees as Explanations
por: Nemecek, Jiri, et al.
Publicado: (2023)

Tuning for Trustworthiness -- Balancing Performance and Explanation Consistency in Neural Network Optimization
por: Hinterleitner, Alexander, et al.
Publicado: (2025)

Shape-aware Graph Spectral Learning
por: Xu, Junjie, et al.
Publicado: (2023)