HGAttack: Transferable Heterogeneous Graph Adversarial Attack (2401.09945v1)
Abstract: Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is crucial. However, existing adversarial attack methods, which are primarily designed for homogeneous graphs, fall short when applied to HGNNs due to their limited ability to address the structural and semantic complexity of HGNNs. This paper introduces HGAttack, the first dedicated gray box evasion attack method for heterogeneous graphs. We design a novel surrogate model to closely resemble the behaviors of the target HGNN and utilize gradient-based methods for perturbation generation. Specifically, the proposed surrogate model effectively leverages heterogeneous information by extracting meta-path induced subgraphs and applying GNNs to learn node embeddings with distinct semantics from each subgraph. This approach improves the transferability of generated attacks on the target HGNN and significantly reduces memory costs. For perturbation generation, we introduce a semantics-aware mechanism that leverages subgraph gradient information to autonomously identify vulnerable edges across a wide range of relations within a constrained perturbation budget. We validate HGAttack's efficacy with comprehensive experiments on three datasets, providing empirical analyses of its generated perturbations. Outperforming baseline methods, HGAttack demonstrated significant efficacy in diminishing the performance of target HGNN models, affirming the effectiveness of our approach in evaluating the robustness of HGNNs against adversarial attacks.
- Fast gradient attack on network embedding. arXiv preprint arXiv:1809.02797, 2018.
- Adversarial attack on graph structured data. In International conference on machine learning, pages 1115–1124. PMLR, 2018.
- Why do adversarial attacks transfer? explaining transferability of evasion and poisoning attacks. In 28th USENIX security symposium (USENIX security 19), pages 321–338, 2019.
- metapath2vec: Scalable representation learning for heterogeneous networks. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pages 135–144, 2017.
- Learning graphs from data: A signal representation perspective. IEEE Signal Processing Magazine, 36(3):44–63, 2019.
- Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding. In Proceedings of The Web Conference 2020, pages 2331–2341, 2020.
- Heterogeneous graph transformer. In Proceedings of The Web Conference 2020, pages 2704–2710, 2020.
- Prohibited item detection via risk graph structure learning. In Proceedings of the ACM Web Conference 2022, pages 1434–1443, 2022.
- Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
- Revisiting graph adversarial attack and defense from a data distribution perspective. In The Eleventh International Conference on Learning Representations, 2022.
- Are we really making much progress? revisiting, benchmarking and refining heterogeneous graph neural networks. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 1150–1160, 2021.
- Modeling relational data with graph convolutional networks. In The Semantic Web: 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3–7, 2018, Proceedings 15, pages 593–607. Springer, 2018.
- Task and model agnostic adversarial attack on graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 15091–15099, 2023.
- Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.
- Attacking graph-based classification via manipulating the graph structure. In Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, pages 2023–2040, 2019.
- How powerful are spectral graph neural networks. In International Conference on Machine Learning, pages 23341–23362. PMLR, 2022.
- Heterogeneous graph attention network. In The world wide web conference, pages 2022–2032, 2019.
- Collaborative knowledge distillation for heterogeneous information network embedding. In Proceedings of the ACM Web Conference 2022, pages 1631–1639, 2022.
- Adversarial attacks and defenses on graphs: A review, a tool, and empirical studies. In arXiv: 2003.00653 (Dec, page 00653. 2020.
- Adversarial examples on graph data: Deep insights into attack and defense. arXiv preprint arXiv:1903.01610, 2019.
- Topology attack and defense for graph neural networks: An optimization perspective. arXiv preprint arXiv:1906.04214, 2019.
- Simple and efficient heterogeneous graph neural network. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 10816–10824, 2023.
- Key player identification in underground forums over attributed heterogeneous information network embedding framework. In Proceedings of the 28th ACM international conference on information and knowledge management, pages 549–558, 2019.
- Robust heterogeneous graph neural networks against adversarial attacks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 4363–4370, 2022.
- Adversarial attacks on neural networks for graph data. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pages 2847–2856, 2018.
- Adversarial attacks on graph neural networks: Perturbations and their patterns. ACM Transactions on Knowledge Discovery from Data (TKDD), 14(5):1–31, 2020.