ml_privacy_meter
Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
AI summary
Privacy Auditor
An auditing tool to assess the privacy risks of machine learning models
- stars
- 613
- forks
- 103
- watching
- 19
Similar projects
Found by comparing what the projects do, not just their names.
Privacy library
A Python library for training machine learning models while preserving the privacy of sensitive data
Bias detection tool
This project investigates how bias can be introduced and spread in machine learning models during federated learning, and aims to detect and mitigate this issue.
Model memorization analysis
A Python package for measuring memorization in Large Language Models.
Privacy tool
A Python implementation of a tool designed to provide anonymity and privacy in software development and data analysis.
Benchmarking
A platform for private benchmarking of machine learning models with different trust levels.
Model evaluator
Evaluates and compares the performance of multimodal large language models on various tasks
Privacy-preservation SVM
Implementing an SVM model to make predictions on encrypted data while preserving the client's privacy
Bias auditor
A software package for auditing and analyzing machine learning models to detect unfair biases
Privacy protector
An open-source implementation of a federated learning framework to protect data privacy in embodied agent learning for Vision-and-Language Navigation.
API Monitor
An integration client providing real-time monitoring and analysis of OpenAI API usage
Secure ML repo
A curated collection of resources and libraries for secure machine learning research and development
Model auditor
An auditing toolbox to assess the fairness of black-box predictive models
Private linear regression algorithm
Secure Linear Regression in the Semi-Honest Two-Party Setting.
ML model transparency
Teaching software developers how to build transparent and explainable machine learning models using Python
Bias detector
A dataset and benchmarking framework to evaluate the performance of question answering models on detecting and mitigating social biases.
