simran-arora/focus
This repo contains code for the paper: "Can Foundation Models Help Us Achieve Perfect Secrecy?"
This project explores how large pre-trained language models can be used to create personalized machine learning models while keeping individual user data private. It takes public or private datasets, like text or images, and applies foundation models using "in-context learning" to evaluate their privacy performance. The primary user for this is a machine learning researcher or privacy engineer interested in the intersection of foundation models and data privacy.
No commits in the last 6 months.
Use this if you are a machine learning researcher evaluating the privacy implications of using foundation models for personalized tasks.
Not ideal if you are a practitioner looking for a ready-to-use, production-grade privacy-preserving machine learning solution.
Stars
24
Forks
4
Language
Python
License
—
Category
Last pushed
Feb 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/simran-arora/focus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tensorflow/privacy
Library for training machine learning models with privacy for training data
meta-pytorch/opacus
Training PyTorch models with differential privacy
tf-encrypted/tf-encrypted
A Framework for Encrypted Machine Learning in TensorFlow
awslabs/fast-differential-privacy
Fast, memory-efficient, scalable optimization of deep learning with differential privacy
privacytrustlab/ml_privacy_meter
Privacy Meter: An open-source library to audit data privacy in statistical and machine learning...