# Adversarial Defense Framework for Graph Neural Network

arXiv: https://arxiv.org/abs/1905.03679 · HTML: https://mlsanity.com/paper/1905.03679/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2019.

## Built on by (most cited first, 8 of 8)

- [Topological Relational Learning on Graphs](https://mlsanity.com/paper/2110.15529/) (2021)
- [Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision](https://mlsanity.com/paper/2203.03762/) (2022)
- [Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective](https://mlsanity.com/paper/2105.08007/) (2021)
- [Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective](https://mlsanity.com/paper/2201.08557/) (2022)
- [Learning Robust Representation through Graph Adversarial Contrastive Learning](https://mlsanity.com/paper/2201.13025/) (2022)
- [Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses](https://mlsanity.com/paper/2508.19641/) (2025)
- [Spatio-Temporal Sparsification for General Robust Graph Convolution Networks](https://mlsanity.com/paper/2103.12256/) (2021)
- [REGE: A Method for Incorporating Uncertainty in Graph Embeddings](https://mlsanity.com/paper/2412.05735/) (2024)

## Abstract (arXiv)

Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities and defense GNN against the adversarial attacks? In this paper, we propose DefNet, an effective adversarial defense framework for GNNs. In particular, we first investigate the latent vulnerabilities in every layer of GNNs and propose corresponding strategies including dual-stage aggregation and bottleneck perceptron. Then, to cope with the scarcity of training data, we propose an adversarial contrastive learning method to train the GNN in a conditional GAN manner by leveraging the high-level graph representation. Extensive experiments on three public datasets demonstrate the effectiveness of DefNet in improving the robustness of popular GNN variants, such as Graph Convolutional Network and GraphSAGE, under various types of adversarial attacks.