Ctrlk
WebsiteLibrariesDevelopersSupport
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Demos and Tutorials

This section lists several demos that apply Concrete ML to some popular machine learning problems. They show how to build ML models that perform well under FHE constraints, and then how to perform the conversion to FHE.

Simpler tutorials that discuss only model usage and compilation are also available for built-in models and deep learning.

Cover

GPT-2 in FHE

Privacy-preserving text generation based on a user's prompt

Cover

Titanic

Train an XGB classifier that can perform encrypted prediction for the Kaggle Titanic competition

Cover

Neural Network Fine-tuning

Fine-tune a VGG network to classify the CIFAR image data-sets and predict on encrypted data

Cover

Neural Network Splitting for SaaS deployment

Train a VGG-like CNN that classifies CIFAR10 encrypted images, and where an initial feature extractor is executed client-side

Cover

Handwritten digit classification

Train a neural network model to classify encrypted digit images from the MNIST data-set

Cover

Encrypted Image filtering

A Hugging Face space that applies a variety of image filters to encrypted images

Cover

Encrypted sentiment analysis

A Hugging Face space that securely analyzes the sentiment expressed in a short text

Cover

Credit Scoring

Predict the chance of a given loan applicant defaulting on loan repayment

Cover

Healthcare diagnosis

Give a diagnosis using FHE to preserve the privacy of the patient

PreviousInference in the Cloud
NextLinear Models

Last updated

Was this helpful?