trucndt/ami
Codebase for Active Membership Inference Attack under Local Differential Privacy in Federated Learning
This project helps evaluate the privacy risks of federated learning systems. It takes a trained federated learning model and a dataset, then attempts to determine if specific individual data records were used in the model's training. This is useful for privacy researchers and machine learning engineers who design or audit federated learning systems.
No commits in the last 6 months.
Use this if you need to assess the vulnerability of a federated learning model to membership inference attacks, especially when local differential privacy mechanisms are in place.
Not ideal if you are looking for a general-purpose privacy-preserving machine learning library or a tool for data anonymization outside of federated learning contexts.
Stars
12
Forks
2
Language
Python
License
—
Category
Last pushed
Feb 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/trucndt/ami"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google/scaaml
SCAAML: Side Channel Attacks Assisted with Machine Learning
pralab/secml
A Python library for Secure and Explainable Machine Learning
Koukyosyumei/AIJack
Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)
AI-SDC/SACRO-ML
Collection of tools and resources for managing the statistical disclosure control of trained...
oss-slu/mithridatium
Mithridatium is a research-driven project aimed at detecting backdoors and data poisoning in...