Visual Blocks for ML is a Google visual programming framework that lets you create ML pipelines in a no-code graph editor. You – and your users – can quickly prototype workflows by connecting drag-…

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

Leaf: A Benchmark for Federated Settings

Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)

Source code and demonstrations for our paper "Dropout is NOT All You Need to Prevent Gradient Leakage".

Official implementation of "Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective"

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

Training data extraction on GPT-2

Code for Findings-ACL 2023 paper: Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence

The code for "Improved Deep Leakage from Gradients" (iDLG).

General Multi-label Image Classification with Transformers

Official implementation of paper "Query2Label: A Simple Transformer Way to Multi-Label Classification".