zhangzp9970/MIA

Unofficial pytorch implementation of paper: Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures

46
/ 100
Emerging

This project helps evaluate the privacy risks of machine learning models. It takes a trained model and its confidence scores as input, then attempts to reconstruct the original training data, such as a person's face from a facial recognition model. This is for machine learning researchers and privacy engineers who need to assess model vulnerabilities.

No commits in the last 6 months.

Use this if you need to understand how vulnerable your machine learning models are to privacy breaches where sensitive training data might be reconstructed.

Not ideal if you are looking for a tool to implement robust privacy-preserving machine learning techniques, as this focuses on demonstrating vulnerabilities.

model-privacy data-reconstruction-attack machine-learning-security privacy-assessment
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

58

Forks

32

Language

Python

License

GPL-3.0

Last pushed

Sep 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zhangzp9970/MIA"

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