nowfound

Life & fun · April 16, 2019

Encrypted Deep Learning Classification with PyTorch and PySyft

Update as of November 18, 2021: The version of PySyft mentioned in this post has been deprecated. Any implementations using this older version of PySyft are…

Encrypted Deep Learning Classification with PyTorch and PySyft launched on April 16, 2019 with 10 votes, #986 of 3,128 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 7 years on.

In plain words

This is a deprecated blog post demonstrating encrypted deep learning classification using PyTorch and PySyft. It shows how to build a private neural network that classifies MNIST images through Secure Multi-Party Computation, achieving classification in under 33 milliseconds with over 98% accuracy. The post is intended for developers interested in privacy-preserving machine learning, though the PySyft version discussed is no longer supported and has been superseded by newer releases.

written from the facts on this page · September 2026

From the sources

Update as of November 18, 2021: The version of PySyft mentioned in this post has been deprecated. Any implementations using this older version of PySyft are unlikely to work. Stay tuned for the release of PySyft 0.6.0, a data centric library for use in production targeted for release in early December. Summary: Great theories need great implementations. We show in this blog how to use a private neural network to classify MNIST images using Secure Multi-Party Computation (SMPC). We achieve classification in <33ms with >98% accuracy over local (virtualized) computation. Note: If you want more posts like this just get in touch with @theoryffel and @OpenMinedOrg . Feel free to follow if you’d…from blog.openmined.org

Does a similar job

all alternatives →

More life & fun this month

the category →

Source: Show HN post ↗

Launched alongside, April 2019

the whole month →