eth-sri/dp-sniper
A machine-learning-based tool for discovering differential privacy violations in black-box algorithms.
This tool helps researchers and privacy engineers evaluate if their "black-box" algorithms are truly differentially private. You provide your algorithm, and it uses machine learning to detect potential privacy leaks, outputting a report on any violations found. The primary users are security researchers and privacy practitioners who develop or audit algorithms designed to protect sensitive data.
No commits in the last 6 months.
Use this if you need to test a black-box algorithm to see if it is leaking private data, even if you don't know its internal workings.
Not ideal if you are looking for a general-purpose differential privacy library to implement private algorithms from scratch.
Stars
24
Forks
5
Language
Python
License
MIT
Category
Last pushed
May 26, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/eth-sri/dp-sniper"
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...