# Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks

arXiv: https://arxiv.org/abs/2009.10235 · HTML: https://mlsanity.com/paper/2009.10235/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2020.

## Built on by (most cited first, 15 of 15)

- [A Survey on Uncertainty Quantification Methods for Deep Learning](https://mlsanity.com/paper/2302.13425/) (2023)
- [Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification](https://mlsanity.com/paper/2110.14012/) (2021)
- [Are Defenses for Graph Neural Networks Robust?](https://mlsanity.com/paper/2301.13694/) (2023)
- [Uncertainty in Graph Neural Networks: A Survey](https://mlsanity.com/paper/2403.07185/) (2024)
- [Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift](https://mlsanity.com/paper/2111.12951/) (2021)
- [Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks](https://mlsanity.com/paper/2302.02829/) (2023)
- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges](https://mlsanity.com/paper/2203.12852/) (2022)
- [Conformalized Link Prediction on Graph Neural Networks](https://mlsanity.com/paper/2406.18763/) (2024)
- [Identifying Ambiguous Similarity Conditions via Semantic Matching](https://mlsanity.com/paper/2204.04053/) (2022)
- [Graph Convolutional Network with Connectivity Uncertainty for EEG-based Emotion Recognition](https://mlsanity.com/paper/2310.14165/) (2023)
- [When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning](https://mlsanity.com/paper/2409.14161/) (2024)
- [Attention-based graph neural networks: a survey](https://mlsanity.com/paper/2605.08679/) (2026)
- [Prompt2Gaussia: Uncertain Prompt-learning for Script Event Prediction](https://mlsanity.com/paper/2308.02103/) (2023)
- [Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation](https://mlsanity.com/paper/2605.05534/) (2026)

## Abstract (arXiv)

With the increasing popularity of graph-based learning, graph neural networks (GNNs) emerge as the essential tool for gaining insights from graphs. However, unlike the conventional CNNs that have been extensively explored and exhaustively tested, people are still worrying about the GNNs' robustness under the critical settings, such as financial services. The main reason is that existing GNNs usually serve as a black-box in predicting and do not provide the uncertainty on the predictions. On the other side, the recent advancement of Bayesian deep learning on CNNs has demonstrated its success of quantifying and explaining such uncertainties to fortify CNN models. Motivated by these observations, we propose UAG, the first systematic solution to defend adversarial attacks on GNNs through identifying and exploiting hierarchical uncertainties in GNNs. UAG develops a Bayesian Uncertainty Technique (BUT) to explicitly capture uncertainties in GNNs and further employs an Uncertainty-aware Attention Technique (UAT) to defend adversarial attacks on GNNs. Intensive experiments show that our proposed defense approach outperforms the state-of-the-art solutions by a significant margin.