Stars
PrivacyGuard platform for Privacy Attacks and Analysis. Perform privacy analyses of ML models using Inference Attacks and Extraction Attacks. PrivacyGuard library implements varied, SotA privacy at…
Main repository for "DProvDB: Differentially Private Query Processing with Multi-Analyst Provenance", accepted to appear in Proc. of the ACM on Management of Data (PACMMOD/SIGMOD'2024)
Maliciously-Secure Multi-Party Computation (MPC) Engine using Authenticated Garbling
A maliciously secure two-party computation engine which is embeddable and accessible
Raft distributed consensus algorithm implemented in Rust.
Effective caching in differentially-private databases (SOSP '23)
The core library of differential privacy algorithms powering the OpenDP Project.
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.
Concrete: TFHE Compiler that converts python programs into FHE equivalent
Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry lead…
Code for hands-on experience with reconstruction attacks in a simple setting
DPLab: Benchmarking Differential Privacy Aggregation Operations
The Privacy Adversarial Framework (PAF) is a knowledge base of privacy-focused adversarial tactics and techniques. PAF is heavily inspired by MITRE ATT&CK®.
An Implementation of Incremental Distributed Point Functions in C++
Programming language for literate programming law specification
Simplified Implementation of Facebook's TAO, but encrypted
Benchmark for differential privacy budget schedulers, based on an Alibaba cluster trace. Used in DPack (EuroSys '25).
This document describes the Distributed Aggregation Protocol (DAP) being developed by the PPM working group at IETF.