Stars
Dataframes powered by a multithreaded, vectorized query engine, written in Rust
Occlum is a memory-safe, multi-process library OS for Intel SGX
Graphene / Graphene-SGX - a library OS for Linux multi-process applications, with Intel SGX support
Probabilistic programming system for fast and exact symbolic inference
Code for computing tight guarantees for differential privacy
A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.
Bayesian Modeling and Probabilistic Programming in Python
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
Statistics of acceptance rate for the top conferences: Oakland, CCS, USENIX Security, NDSS.
DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.
list of differential-privacy related resources
A computer algebra system written in pure Python
Density Ratio Estimation via Infinitesimal Classification (AISTATS 2022 Oral)
links to conference publications in graph-based deep learning
Differentially Private (tabular) Generative Models Papers with Code
Helper library for LangSmith that provides an interface to run evaluations by simply writing config files.
A machine-learning-based tool for discovering differential privacy violations in black-box algorithms.
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
A repo lists papers related to LLM based agent
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
oneAPI Deep Neural Network Library (oneDNN)