paper-with-me

Papers

GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injections

2022-10-23 · Junyuan Fang, Haixian Wen, Jiajing Wu, Qi Xuan, Zibin Zheng, Chi K. Tse

Graph neural networks (GNNs) have found successful applications in various graph-related tasks. However, recent studies have shown that many GNNs are vulnerable to adversarial attacks. In a vast majority of existing studies, adversarial attacks on GNNs are launched via direct modification of the original graph such as adding/removing links, which may not be applicable in practice. In this paper, we focus on a realistic attack operation via injecting fake nodes. The proposed Global Attack strategy via Node Injection (GANI) is designed under the comprehensive consideration of an unnoticeable perturbation setting from both structure and feature domains. Specifically, to make the node injections as imperceptible and effective as possible, we propose a sampling operation to determine the degree of the newly injected nodes, and then generate features and select neighbors for these injected nodes based on the statistical information of features and evolutionary perturbations obtained from a genetic algorithm, respectively. In particular, the proposed feature generation mechanism is suitable for both binary and continuous node features. Extensive experimental results on benchmark datasets against both general and defended GNNs show strong attack performance of GANI. Moreover, the imperceptibility analyses also demonstrate that GANI achieves a relatively unnoticeable injection on benchmark datasets.

📄 PDF Abstract BibTeX arXiv:2210.12598

Code (1)

alexfanjn/gani 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification

2025-09-30 · Xiaobao Wang, Ruoxiao Sun, Yujun Zhang, Bingdao Feng 외 arxiv

Graph Neural Networks (GNNs) have demonstrated strong performance across tasks such as node classification, link prediction, and graph classification, but remain vulnerable to backdoor attacks that implant imperceptible …

Graph ClassificationNode ClassificationAnomaly DetectionLink Prediction

Adversarial Attacks on Deep Graph Matching

2020-12-01 · NeurIPS 2020 12 · Zijie Zhang, Zeru Zhang, Yang Zhou, Yelong Shen 외

Despite achieving remarkable performance, deep graph learning models, such as node classification and network embedding, suffer from harassment caused by small adversarial perturbations. However, the vulnerability analys…

Adversarial AttackDensity EstimationGraph LearningGraph Matching+3

Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)

2025-08-06 · Iyiola E. Olatunji, Franziska Boenisch, Jing Xu, Adam Dziedzic arxiv

Large Language Models (LLMs) are increasingly integrated with graph-structured data for tasks like node classification, a domain traditionally dominated by Graph Neural Networks (GNNs). While this integration leverages r…

Node ClassificationAdversarial Attack

Debiased Graph Poisoning Attack via Contrastive Surrogate Objective

2024-07-27 · Kanghoon Yoon, Yeonjun In, Namkyeong Lee, Kibum Kim 외

Graph neural networks (GNN) are vulnerable to adversarial attacks, which aim to degrade the performance of GNNs through imperceptible changes on the graph. However, we find that in fact the prevalent meta-gradient-based …

Similarity Preserving Adversarial Graph Contrastive Learning

2023-06-24 · Yeonjun In, Kanghoon Yoon, Chanyoung Park

Recent works demonstrate that GNN models are vulnerable to adversarial attacks, which refer to imperceptible perturbation on the graph structure and node features. Among various GNN models, graph contrastive learning (GC…

Adversarial RobustnessContrastive Learning