Research map / Adversarial robustness and security / Attacks on text and graphs
Adversarial Attacks on Deep Graph Matching
Zijie Zhang, Zeru Zhang, Yang Zhou, Yelong Shen, Ruoming Jin, Dejing Dou
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| add KDE density maximization and MLPGD to PGD attack (full GMA) (ablation) | GMA-PGD · AS, SNS, DBLP with SNNA and DGMC | mismatching rate / Precision@30: GMA > 54.9% (AS), > 55.7% (SNS), > 74.2% (DBLP) | Improved |
| add MLPGD starting-point search to PGD (ablation) | GMA-PGD · SNS ablation | mismatching rate / Precision@30 | Improved |
| KDE-only variant vs MLPGD-only variant (ablation) | GMA-KDE vs GMA-MLPGD · SNS ablation | mismatching rate / Precision@30 | Improved |
| increase perturbation budget epsilon from 1 to 5 (ablation) | GMA · Precision@30 | Precision@30 (lower is stronger attack) | Improved |
| increase meta step size alpha (ablation) | MLPGD · three dataset groups | mismatching rate / Precision@30 | Mixed |
Closest papers by meaning
- Adversarial Attacks on Graph Neural Networks via Meta Learning (ICLR 2019 · similarity 0.90)
- Value at Adversarial Risk: A Graph Defense Strategy against Cost-Aware Attacks (AAAI 2024 · similarity 0.90)
- Adversarial Attacks on Node Embeddings via Graph Poisoning (ICML 2019 · similarity 0.90)
- Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions (NeurIPS 2023 · similarity 0.90)
- Adversarial Attack on Graph Structured Data (ICML 2018 · similarity 0.89)
- Adversarial Contrastive Graph Masked AutoEncoder Against Graph Structure and Feature Dual Attacks (AAAI 2025 · similarity 0.87)
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.
