AndrewZhou924/Awesome-model-inversion-attack

[arXiv:2411.10023] "Model Inversion Attacks: A Survey of Approaches and Countermeasures"

31
/ 100
Emerging

When you use machine learning models, you expect the private data they were trained on to stay private. However, model inversion attacks can reconstruct this sensitive training data by analyzing a deployed model. This curated list compiles research papers, tools, and code related to these attacks across various domains like computer vision and natural language processing. It helps privacy researchers and machine learning engineers understand and counteract these threats.

217 stars. No commits in the last 6 months.

Use this if you are a researcher or practitioner concerned with the privacy implications of deployed machine learning models and need to understand the latest techniques for model inversion attacks and their defenses.

Not ideal if you are looking for a plug-and-play software tool for immediate implementation without deep dives into research papers.

AI-privacy machine-learning-security data-confidentiality model-auditing data-reconstruction
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

217

Forks

15

Language

License

Last pushed

May 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AndrewZhou924/Awesome-model-inversion-attack"

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