Structure-Aware Robustness Certificates for Graph Classification
Not on the map. Why?
Abstract (arXiv)
Certifying the robustness of a graph-based machine learning model poses a critical challenge for safety. Current robustness certificates for graph classifiers guarantee output invariance with respect to the total number of node pair flips (edge addition or edge deletion), which amounts to an l0 ball centred on the adjacency matrix. Although theoretically attractive, this type of isotropic structural noise can be too restrictive in practical scenarios where some node pairs are more critical than others in determining the classifier's output. The certificate, in this case, gives a pessimistic depiction of the robustness of the graph model. To tackle this issue, we develop a randomised smoothing method based on adding an anisotropic noise distribution to the input graph structure. We show that our process generates structural-aware certificates for our classifiers, whereby the magnitude of robustness certificates can vary across different pre-defined structures of the graph. We demonstrate the benefits of these certificates in both synthetic and real-world experiments.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 36 references that are in the map. First posted on arXiv 20 Jun 2023.
Builds on
16 of 36 references.
References · 16
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
- 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
- 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 179
- 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
- 2019Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifierscited by 65
- 2021Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Boundscited by 65
- 2019Certifiable Robustness to Graph Perturbationscited by 62
- 2019Certifiable Robustness and Robust Training for Graph Convolutional Networkscited by 59
- 2020Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbationcited by 57
- 2020Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and Morecited by 56
4 more
- 2020Second-Order Provable Defenses against Adversarial Attackscited by 40
- 2020Learning to Solve Combinatorial Optimization Problems on Real-World Graphs in Linear Timecited by 39
- 2020Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothingcited by 29
- 2020Certified Robustness of Graph Classification against Topology Attack with Randomized Smoothingcited by 12
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.