CrypTen — Safe machine studying with PyTorch
This method of encryption and data security is required for ML researchers who work with data that needs to be kept secure, such as medical information or rewards that contain sensitive information that cannot be disclosed for privacy reasons.
Where is it used?
Facebook made CrypTen open source in October 2019, enabling our researchers to create contextual bandit models that protect privacy. These models help improve functions such as Facebook’s ranking algorithm without revealing our users’ personal data.
Where can I find out more?
To learn more about CrypTen, visit their website, which includes documentation and the installation script. CrypTen’s GitHub repository goes into more detail with examples and tutorials on how to integrate CrypTen with PyTorch libraries and how to use the framework. Also, join their Slack community to stay up to date with the latest information.
To delve deep into CrypTen protocols and designs, check out this blog article or paper.
If you have any further questions about CrypTen, please let us know on our YouTube channel or on Twitter. We always want to hear from you, and we hope you find this open source project and the new ELI5 series useful.
About the ELI5 series
In a series of short videos (approx. 1 minute long) one of our developer advocates in the Facebook Open Source Team explains a Facebook Open Source project in an easy to understand and user-friendly way.
For each of these videos we will write an accompanying blog post (like the one you are reading now), which you can find on our YouTube channel.
To learn more about Facebook Open Source, visit our open source site, subscribe to our YouTube channel, or follow us on Twitter and Facebook.
Interested in working with open source on Facebook? Check out our open source related job postings on our careers page by taking this short survey.