Conference item
Adversarial attacks on graph classification via Bayesian optimisation
- Abstract:
- Graph neural networks, a popular class of models effective in a wide range of graph-based learning tasks, have been shown to be vulnerable to adversarial attacks. While the majority of the literature focuses on such vulnerability in node-level classification tasks, little effort has been dedicated to analysing adversarial attacks on graph-level classification, an important problem with numerous real-life applications such as biochemistry and social network analysis. The few existing methods often require unrealistic setups, such as access to internal information of the victim models, or an impractically-large number of queries. We present a novel Bayesian optimisation-based attack method for graph classification models. Our method is black-box, query-efficient and parsimonious with respect to the perturbation applied. We empirically validate the effectiveness and flexibility of the proposed method on a wide range of graph classification tasks involving varying graph properties, constraints and modes of attack. Finally, we analyse common interpretable patterns behind the adversarial samples produced, which may shed further light on the adversarial robustness of graph classification models. An open-source implementation is available at https://github.com/xingchenwan/grabnel.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Version of record, pdf, 1.4MB, Terms of use)
-
Authors
- Publisher:
- Neural Information Processing Systems Foundation
- Host title:
- Proceedings of Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
- Volume:
- 34
- Pages:
- 6983-6996
- Publication date:
- 2021-01-01
- Event title:
- Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
- Event location:
- Virtual event
- Event start date:
- 2021-12-06
- Event end date:
- 2021-12-14
- ISSN:
-
1049-5258
- ISBN:
- 9781713845393
- Language:
-
English
- Keywords:
- Pubs id:
-
1266392
- Local pid:
-
pubs:1266392
- Deposit date:
-
2023-10-08
- ARK identifier:
Terms of use
- Copyright holder:
- Wan et al.
- Copyright date:
- 2021
- Rights statement:
- Copyright © 2021 The Author(s).
If you are the owner of this record, you can report an update to it here: Report update to this record