Attacking Graph Convolutional Networks via Rewiring

2019/06/10 by Yao Ma, Ma, Yao, Suhang Wang +7 · 6 citations
Computer Science · Mathematics · #Advanced Graph Neural Networks #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Network Security and Intrusion Detection #cs.CR #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1906.03750

openalex publication_date 2019/06/10 · arxiv created 2019/09/28 · arxiv updated 2019/10/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification. Recent researches show that graph neural networks are vulnerable to adversarial attacks, which deliberately add carefully created unnoticeable perturbation to the graph structure. The perturbation is usually created by adding/deleting a few edges, which might be noticeable even when the number of edges modified is small. In this paper, we propose a graph rewiring operation which affects the graph in a less noticeable way compared to adding/deleting edges. We then use reinforcement learning to learn the attack strategy based on the proposed rewiring operation. Experiments on real world graphs demonstrate the effectiveness of the proposed framework. To understand the proposed framework, we further analyze how its generated perturbation to the graph structure affects the output of the target model.

Citations

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs

Cited by

• Adversarial Attacks on Graph Classification via Bayesian Optimisation
• Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
• Information Obfuscation of Graph Neural Networks
• A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
• DeepInsight: Interpretability Assisting Detection of Adversarial Samples on Graphs
• On the Stability of Graph Convolutional Neural Networks under Edge Rewiring

Related

• Unifying Adversarial Perturbation for Graph Neural Networks
• GUAP: Graph Universal Attack Through Adversarial Patching
• Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
• Graph Structure Learning for Robust Graph Neural Networks
• GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning