# On the Robustness of Graph Reduction Against GNN Backdoor

arXiv: https://arxiv.org/abs/2407.02431 · HTML: https://mlsanity.com/paper/2407.02431/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## Builds on (most cited first, 22 of 22)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [A Fair Comparison of Graph Neural Networks for Graph Classification](https://mlsanity.com/paper/1912.09893/) (2019)
- [Rethinking Graph Neural Networks for Anomaly Detection](https://mlsanity.com/paper/2205.15508/) (2022)
- [AliGraph: A Comprehensive Graph Neural Network Platform](https://mlsanity.com/paper/1902.08730/) (2019)
- [Backdoor Attacks to Graph Neural Networks](https://mlsanity.com/paper/2006.11165/) (2020)
- [Graph Backdoor](https://mlsanity.com/paper/2006.11890/) (2020)
- [Scaling Up Graph Neural Networks Via Graph Coarsening](https://mlsanity.com/paper/2106.05150/) (2021)
- [Spectrally approximating large graphs with smaller graphs](https://mlsanity.com/paper/1802.07510/) (2018)
- [A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking](https://mlsanity.com/paper/2210.07494/) (2022)
- [Unnoticeable Backdoor Attacks on Graph Neural Networks](https://mlsanity.com/paper/2303.01263/) (2023)
- [GCN-GAN: A Non-linear Temporal Link Prediction Model for Weighted Dynamic Networks](https://mlsanity.com/paper/1901.09165/) (2019)
- [A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning](https://mlsanity.com/paper/1910.14147/) (2019)
- [Survey on Graph Neural Network Acceleration: An Algorithmic Perspective](https://mlsanity.com/paper/2202.04822/) (2022)
- [NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification](https://mlsanity.com/paper/2103.03939/) (2021)
- [Structure-Preserving Sparsification Methods for Social Networks](https://mlsanity.com/paper/1601.00286/) (2016)
- [PoisonedGNN: Backdoor Attack on Graph Neural Networks-based Hardware Security Systems](https://mlsanity.com/paper/2303.14009/) (2023)
- [Graph Neural Networks for Hardware Vulnerability Analysis -- Can you Trust your GNN?](https://mlsanity.com/paper/2303.16690/) (2023)

## Built on by (most cited first, 1 of 1)

- [On the Adversarial Robustness of Graph Neural Networks with Graph Reduction](https://mlsanity.com/paper/2412.05883/) (2024)

## Abstract (arXiv)

Graph Neural Networks (GNNs) are gaining popularity across various domains due to their effectiveness in learning graph-structured data. Nevertheless, they have been shown to be susceptible to backdoor poisoning attacks, which pose serious threats to real-world applications. Meanwhile, graph reduction techniques, including coarsening and sparsification, which have long been employed to improve the scalability of large graph computational tasks, have recently emerged as effective methods for accelerating GNN training on large-scale graphs. However, the current development and deployment of graph reduction techniques for large graphs overlook the potential risks of data poisoning attacks against GNNs. It is not yet clear how graph reduction interacts with existing backdoor attacks. This paper conducts a thorough examination of the robustness of graph reduction methods in scalable GNN training in the presence of state-of-the-art backdoor attacks. We performed a comprehensive robustness analysis across six coarsening methods and six sparsification methods for graph reduction, under three GNN backdoor attacks against three GNN architectures. Our findings indicate that the effectiveness of graph reduction methods in mitigating attack success rates varies significantly, with some methods even exacerbating the attacks. Through detailed analyses of triggers and poisoned nodes, we interpret our findings and enhance our understanding of how graph reduction influences robustness against backdoor attacks. These results highlight the critical need for incorporating robustness considerations in graph reduction for GNN training, ensuring that enhancements in computational efficiency do not compromise the security of GNN systems.