Uniform Manifold Approximation and Projection

The full minitorch student suite.

Breaching privacy in federated learning scenarios for vision and text

GradAttack is a Python library for easy evaluation of privacy risks in public gradients in Federated Learning, as well as corresponding mitigation strategies.

A comprehensive toolbox for model inversion attacks and defenses, which is easy to get started.

[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, D…

Membership Inference, Attribute Inference and Model Inversion attacks implemented using PyTorch.

This repository contains Python code for the paper "Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning".

The implementation for paper Joint t-SNE for Comparable Projections of Multiple High-Dimensional Datasets.