SACRO-ML

This repository aims to map the ecosystem of artificial intelligence guidelines, principles, codes of ethics, standards, regulation and beyond.

An extensible framework for application-level data management on Kubernetes, Kanister is a Cloud Native Computing Foundation sandbox project and was originally created by the Veeam Kasten team.

Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.

DAR - Disk ARchive

[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation" by Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu

? Model-Driven test data generation platform enabling developers to create realistic, scalable, and privacy-compliant test data. Features model-driven data generation, GDPR compliance, and seamless Python integration.

"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning" by Chongyu Fan*, Jiancheng Liu*, Licong Lin*, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu

Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs (ACM CCS'21)

Location Privacy Meter: A tool to model human mobility and quantify location privacy

Deliveres functionality to securely fetch and provide 3rd Party resources as well as proxying requests back to the 3rd Party Provider. This is the base library you use as a dependency within your own Privacy Proxy project. See the docs and the examples project to implement your own.