safe-graph/graph-adversarial-learning-literature

A curated list of adversarial attacks and defenses papers on graph-structured data.

41
/ 100
Emerging

This is a comprehensive collection of research papers focused on making machine learning models that operate on graph data more robust against attacks, and also on developing methods to attack them. It provides a list of papers, categorized by whether they describe an attack or a defense, helping you understand vulnerabilities and protective measures for graph-based AI. Researchers and practitioners working with graph neural networks in fields like social network analysis, fraud detection, or drug discovery would find this resource useful.

861 stars. No commits in the last 6 months.

Use this if you are a researcher or AI practitioner investigating the security and robustness of machine learning models built on graph-structured data, and need to find the latest research on adversarial attacks and defenses.

Not ideal if you are looking for ready-to-use software libraries or practical guides for implementing graph machine learning solutions, as this resource focuses purely on academic literature.

Graph AI security Adversarial machine learning Graph neural networks AI robustness Machine learning research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 23 / 25

How are scores calculated?

Stars

861

Forks

131

Language

License

Last pushed

Dec 15, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/safe-graph/graph-adversarial-learning-literature"

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