Skip to content
Book Open access

Graph Adversarial Defense with Virtual Spectral Anchor Injection

Aug 2026 · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · pp. 5326-5337 · 0 citations · 54 references

TL;DR

An active paradigm that repurposes the offensive tactic of node injection into a structural defense, ANIE significantly enhances GNN robustness, outperforming state-of-the-art defenses by up to 2× in classification accuracy under poisoning and evasion attacks.

Abstract

Graph Neural Networks (GNNs) have demonstrated superior performance in various graph learning tasks such as node classification and link prediction. However, recent studies have shown that GNNs are highly vulnerable to graph adversarial attacks. To enhance the robustness of GNNs, existing defense strategies have primarily focused on adversarial training on graph data, graph purification, or certifiable robustness. Different from the conventional defense paradigms, we propose Anchor Node Injection Enhancement (ANIE), an active paradigm that repurposes the offensive tactic of node injection into a structural defense. ANIE injects virtual ''auxiliary anchor nodes'' to stabilize the graph's spectral manifold through Dirichlet energy minimization. By establishing robust class prototypes, ANIE reinforces class-wise structural stability and guides perturbed nodes back to correct manifolds. As an attack-agnostic and ''plug-and-play'' framework, ANIE requires no physical modification of the original graph and generalizes to both transductive and inductive settings. Empirical results across multiple benchmarks demonstrate that ANIE significantly enhances GNN robustness, outperforming state-of-the-art defenses by up to 2× in classification accuracy under poisoning and evasion attacks.

Read PDF

Similar papers

Conference Open access Aug 2026

A Cross-Domain Adversarial-Resilient Graph Reduction Framework for Robust GNN-Based Node Classification

This paper proposes a robust graph reduction framework that enhances adversarial resilience by combining gradient-based node importance estimation with graph structure reduction, and shows that the reduced graph achieves higher clean classification accuracy than the full graph, while substantially reducing performance...

Lubin Balasubramanian, Suchithra R · 0 citations
Conference Open access Sep 2026

Adversarial Masked Graph Modeling for Robust Graph Autoencoders

This work designs a dual-consistency graph augmentation method that enriches the graph topology to mitigate structural vulnerabilities and presents an adversarial masked autoen-coder to mitigate model overfitting to the perturbed graph.

Qi-Qi Zhang, Chuan-Jin Liu, Gen Liu et al. · 0 citations

Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL

This work proposes a transferable graph purification scheme, named ProGAP, to bridge adversarial defense knowledge via vulnerability-aware graph prompt learning, and achieves 1%-9% improvement, and reduces the time consumption by up to 2.2x.

Shuo-Min Xue, Jing-Yuan Li, Ju Jia et al. · 0 citations
Conference Open access Sep 2026

Adversarial Optimization Scheme for Threat Detection Based on Hierarchical Oracle Supervision

This study introduces an adversarial training optimization framework that incorporates hierarchical label encoding and prompt learning, designed to enhance model robustness and generalization in threat detection.

Yi-Qing Luo, Ming-Shu He, Xiao-Juan Wang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.