Research map / Graph learning / Graph self-supervised learning
Measuring the Privacy Leakage via Graph Reconstruction Attacks on Simplicial Neural Networks (Student Abstract)
Huixin Zhan, Kun Zhang, Keyi Lu, Victor S. Sheng
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Use SNN rather than GCN representations for the reconstruction attack | GRA · CiteSeer | AUC: 0.8832 -> 0.9833 | Improved |
| Use SNN rather than GCN representations for the reconstruction attack | GRA · Cora | AUC: 0.8900 -> 0.9713 | Improved |
| Use SNN rather than GCN representations for the reconstruction attack | GRA · Pubmed | AUC: 0.8937 -> 0.9826 | Improved |
| Use SNN rather than GCN representations for the reconstruction attack | GRA · Computers | AUC: 0.9041 -> 0.9802 | Improved |
| Use SNN rather than GCN representations for the reconstruction attack | GRA · Photos | AUC: 0.9157 -> 0.9832 | Improved |
| Use SNN rather than GAT representations for the reconstruction attack | GRA · CiteSeer | AUC: 0.9224 -> 0.9833 | Improved |
| Use SNN rather than GAT representations for the reconstruction attack | GRA · Cora | AUC: 0.9640 -> 0.9713 | Improved |
| Use SNN rather than GAT representations for the reconstruction attack | GRA · Pubmed | AUC: 0.9704 -> 0.9826 | Improved |
| Use SNN rather than GAT representations for the reconstruction attack | GRA · Computers | AUC: 0.9800 -> 0.9802 | Improved |
| Use SNN rather than GAT representations for the reconstruction attack | GRA · Photos | AUC: 0.9703 -> 0.9832 | Improved |
| Use GAT rather than GCN representations for the reconstruction attack | GRA · CiteSeer | AUC: 0.8832 -> 0.9224 | Improved |
| Use GAT rather than GCN representations for the reconstruction attack | GRA · Cora | AUC: 0.8900 -> 0.9640 | Improved |
Closest papers by meaning
- On provable privacy vulnerabilities of graph representations (NeurIPS 2024 · similarity 0.90)
- GRAIN: Exact Graph Reconstruction from Gradients (ICLR 2025 · similarity 0.88)
- FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks (ICML 2025 · similarity 0.87)
- When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning (AAAI 2025 · similarity 0.86)
- Going Deeper into Locally Differentially Private Graph Neural Networks (ICML 2025 · similarity 0.86)
- GraphIP–Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It? (NeurIPS 2026 · similarity 0.86)
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.
