Buchumschlag

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Li, Jiate, Pang, Meng, Dong, Yun, Jia, Jinyuan, Wang, Binghui
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Cryptography and Security
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
von: Li, Jiate, et al.
Veröffentlicht: (2025)

Graph Neural Network Explanations are Fragile
von: Li, Jiate, et al.
Veröffentlicht: (2024)

AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification
von: Li, Jiate, et al.
Veröffentlicht: (2025)

Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Method
von: Li, Jiate, et al.
Veröffentlicht: (2024)

Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
von: Yang, Yuxin, et al.
Veröffentlicht: (2024)

Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
von: Gosch, Lukas, et al.
Veröffentlicht: (2024)

MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
von: Wang, Yanting, et al.
Veröffentlicht: (2024)

E-SAGE: Explainability-based Defense Against Backdoor Attacks on Graph Neural Networks
von: Yuan, Dingqiang, et al.
Veröffentlicht: (2024)

Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack
von: Liu, Xin, et al.
Veröffentlicht: (2024)

Detecting Complex Multi-step Attacks with Explainable Graph Neural Network
von: Liu, Wei, et al.
Veröffentlicht: (2024)

PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
von: Zou, Wei, et al.
Veröffentlicht: (2024)

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

FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
von: Yang, Yuxin, et al.
Veröffentlicht: (2024)

Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning
von: Nie, Chenfei, et al.
Veröffentlicht: (2024)

Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation
von: Chanda, Dibaloke, et al.
Veröffentlicht: (2023)

Backdoor Attacks on Discrete Graph Diffusion Models
von: Wang, Jiawen, et al.
Veröffentlicht: (2025)

Safeguarding Graph Neural Networks against Topology Inference Attacks
von: Fu, Jie, et al.
Veröffentlicht: (2025)

Provably Robust Multi-bit Watermarking for AI-generated Text
von: Qu, Wenjie, et al.
Veröffentlicht: (2024)

Watermarking Graph Neural Networks via Explanations for Ownership Protection
von: Downer, Jane, et al.
Veröffentlicht: (2025)

A Learning-Based Attack Framework to Break SOTA Poisoning Defenses in Federated Learning
von: Yang, Yuxin, et al.
Veröffentlicht: (2024)

LIPSTICK: Corruptibility-Aware and Explainable Graph Neural Network-based Oracle-Less Attack on Logic Locking
von: Aghamohammadi, Yeganeh, et al.
Veröffentlicht: (2024)

Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks
von: Noorbakhsh, Sayedeh Leila, et al.
Veröffentlicht: (2024)

A Systematic Study of Model Extraction Attacks on Graph Foundation Models
von: Xu, Haoyan, et al.
Veröffentlicht: (2025)

Learning Robust and Privacy-Preserving Representations via Information Theory
von: Zhang, Binghui, et al.
Veröffentlicht: (2024)

Collective Certified Robustness against Graph Injection Attacks
von: Lai, Yuni, et al.
Veröffentlicht: (2024)

EnsembleSHAP: Faithful and Certifiably Robust Attribution for Random Subspace Method
von: Wang, Yanting, et al.
Veröffentlicht: (2026)

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
von: Hong, Hanbin, et al.
Veröffentlicht: (2023)

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks
von: Dong, Xuewen, et al.
Veröffentlicht: (2025)

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
von: Dai, Enyan, et al.
Veröffentlicht: (2022)

Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective
von: Wang, Zifan, et al.
Veröffentlicht: (2024)

Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks
von: Zhang, Jiahao, et al.
Veröffentlicht: (2026)

Hijacking Attacks against Neural Networks by Analyzing Training Data
von: Ge, Yunjie, et al.
Veröffentlicht: (2024)

Node Injection Attack Based on Label Propagation Against Graph Neural Network
von: Zhu, Peican, et al.
Veröffentlicht: (2024)

Provable Privacy Attacks on Trained Shallow Neural Networks
von: Smorodinsky, Guy, et al.
Veröffentlicht: (2024)

A Critical Evaluation of Defenses against Prompt Injection Attacks
von: Jia, Yuqi, et al.
Veröffentlicht: (2025)

On the Adversarial Robustness of Graph Neural Networks with Graph Reduction
von: Wu, Kerui, et al.
Veröffentlicht: (2024)

FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models
von: Wang, Yanting, et al.
Veröffentlicht: (2024)

Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks
von: Lin, Minhua, et al.
Veröffentlicht: (2024)

Backdoor Attacks against Hybrid Classical-Quantum Neural Networks
von: Guo, Ji, et al.
Veröffentlicht: (2024)

ModelShield: Adaptive and Robust Watermark against Model Extraction Attack
von: Pang, Kaiyi, et al.
Veröffentlicht: (2024)