Research map / Adversarial robustness and security / Attacks on text and graphs
Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add robust hinge-loss training to GCN (ablation) | GCN graph classifier · Enzymes | fraction of graphs certified robust | Helped |
| use single linear ReLU relaxation (ENV_Single) instead of double linear approximation (ablation) | convex envelope certificate · Enzymes ReLU, s=3 | fraction of graphs certified robust | Helped |
| use ENV_Single instead of double approximation (ablation) | convex envelope certificate · Enzymes ReLU | computation time | Hurt |
| ADMM attack vs Dai et al. attack | topological attack on GCN · Enzymes | test accuracy under attack | Helped |
| increase training set from 30% to 80% of Enzymes (ablation) | certificate tightness · Enzymes | certificate gap | No clear effect |
Closest papers by meaning
- Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks (ICLR 2024 · similarity 0.93)
- Robust Graph Condensation via Classification Complexity Mitigation (NeurIPS 2025 · similarity 0.92)
- Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks (AAAI 2024 · similarity 0.89)
- On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective (NeurIPS 2025 · similarity 0.89)
- Enhancing Graph Classification Robustness with Singular Pooling (NeurIPS 2025 · similarity 0.89)
- A Simple and Yet Fairly Effective Defense for Graph Neural Networks (AAAI 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.