ChandlerBang/awesome-graph-attack-papers

Adversarial attacks and defenses on Graph Neural Networks.

40
/ 100
Emerging

This resource provides a curated collection of research papers focused on how machine learning models that analyze interconnected data (like social networks or molecular structures) can be intentionally misled, and how to protect them from such attacks. It compiles a comprehensive list of studies detailing various methods to 'trick' these models and techniques to make them more resilient. Researchers and practitioners working with graph-structured data and GNNs will find this useful for understanding security vulnerabilities and developing robust systems.

391 stars. No commits in the last 6 months.

Use this if you are developing, deploying, or researching machine learning models that operate on graph data and need to understand their vulnerabilities to adversarial attacks or how to defend against them.

Not ideal if you are looking for an introductory guide to graph neural networks or general machine learning security without a specific focus on graph-structured data.

graph-machine-learning model-security adversarial-ai network-analysis data-privacy
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

391

Forks

32

Language

License

CC0-1.0

Last pushed

Feb 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ChandlerBang/awesome-graph-attack-papers"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.