Technology

OpenDP

A community-driven library for building privacy-preserving statistical analysis tools using differential privacy.

OpenDP is a collaborative project between Harvard University and Microsoft that provides a robust framework for statistical disclosure limitation. The library (written in Rust with Python bindings) enables researchers to compute accurate aggregates like means, variances, and histograms while maintaining rigorous mathematical privacy guarantees. By implementing vetted algorithms for sensitivity calibration and noise injection, OpenDP allows organizations to share sensitive datasets without risking individual re-identification.

https://opendp.org

What builders pair with OpenDP

Projects using both technologies. Select a pairing to see a project.

Built with OpenDP

CUDA 1 shared project diffprivlib 1 shared project FFmpeg 1 shared project Google Differential Privacy Library 1 shared project GStreamer 1 shared project H 1 shared project

8 more pairings

NVIDIA DeepStream 1 shared project OpenCV 1 shared project PyDP 1 shared project RNN 1 shared project RTSP 1 shared project SmartNoise 1 shared project TensorRT 1 shared project Transfer learning 1 shared project

Pairing: CUDA

Seguridad Infantil: El Uso de Cámaras de Video e IA para el Cuidado de Niños

Bogotá · November 28, 2024

view project | view CUDA

Recent Talks & Demos

Showing 1-1 of 1

Members-Only

Sign in to see who built these projects

Sign in View FAQ

IA en Seguridad y Cuidado Infantil

RNN Transfer learning