Concrete ML
WebsiteLibrariesProducts & ServicesDevelopersSupport
1.9
1.9
  • Welcome
  • Get Started
    • What is Concrete ML?
    • Installation
    • Key concepts
    • Inference in the cloud
  • Built-in Models
    • Linear models
    • Tree-based models
    • Neural networks
    • Nearest neighbors
    • Encrypted dataframe
    • Encrypted training
  • LLMs
    • Inference
    • Encrypted fine-tuning
  • Deep Learning
    • Using Torch
    • Using ONNX
    • Step-by-step guide
    • Debugging models
    • Optimizing inference
  • Guides
    • Prediction with FHE
    • Production deployment
    • Hybrid models
    • Serialization
    • GPU acceleration
  • Tutorials
    • See all tutorials
    • Built-in model examples
    • Deep learning examples
  • References
    • API
  • Explanations
    • Security and correctness
    • Quantization
    • Pruning
    • Compilation
    • Advanced features
    • Project architecture
      • Importing ONNX
      • Quantization tools
      • FHE Op-graph design
      • External libraries
  • Developers
    • Set up the project
    • Set up Docker
    • Documentation
    • Support and issues
    • Contributing
    • Support new ONNX node
    • Release note
    • Feature request
    • Bug report
Powered by GitBook

Libraries

  • TFHE-rs
  • Concrete
  • Concrete ML
  • fhEVM

Developers

  • Blog
  • Documentation
  • Github
  • FHE resources

Company

  • About
  • Introduction to FHE
  • Media
  • Careers
On this page
  • Start here
  • Go further
  • Live demos on Hugging Face:
  • Code examples on Github:
  • Blog tutorials:
  • Video tutorials

Was this helpful?

Export as PDF
  1. Tutorials

See all tutorials

PreviousGPU accelerationNextBuilt-in model examples

Last updated 1 month ago

Was this helpful?

Start here

Go further

Live demos on Hugging Face:

  • : Encrypted anonymization uses Fully Homomorphic Encryption (FHE) to anonymize personally identifiable information (PII) within encrypted documents, enabling computations to be performed on the encrypted data.

    • Check the

  • : Predicting credit scoring card approval application in which sensitive data can be shared and analyzed without exposing the actual information to neither the three parties involved, nor the server processing it.

    • Check the

  • : predicting if an encrypted tweet / short message is positive, negative or neutral, using FHE.

    • Check the and the

  • : giving a diagnosis using FHE to preserve the privacy of the patient based on a patient's symptoms, history and other health factors.

    • Check the

  • : filtering encrypted images by applying filters such as black-and-white, ridge detection, or your own filter.

    • Check the

Code examples on Github:

Blog tutorials:

Video tutorials

Zama 5-Question Developer Survey

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

: Train an XGB classifier that can perform encrypted prediction for the

: Use federated learning to train a Logistic Regression while preserving training data confidentiality. Import the model into Concrete ML and perform encrypted prediction

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

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

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

- April 2024

- February 2024

- June 2023

- June 2023

- May 2023

- February 2023

- November 2022

- August 2022

- May 2024

- February 2024

- June 2023

We want to hear from you! Take 1 minute to share your thoughts and helping us enhance our documentation and libraries. 👉 to participate.

Build-in model examples
Deep learning examples
Encrypted anonymization
code
Credit card approval
code
Sentiment analysis with transformers
code
blog post
Health diagnosis
code
Encrypted image filtering
code
GPT-2 in FHE
Titanic
Kaggle Titanic competition
Federated learning and private inference
Neutral network fine-tuning
Encrypted sentiment analysis
Credit scoring
Running privacy-preserving inferences on Hugging Face endpoints
Build an end-to-end encrypted Shazam application using Concrete ML
Linear regression over encrypted data with homomorphic encryption
Comparison of Concrete ML regressors
How to deploy a machine learning model with Concrete ML
Encrypted image filtering using homomorphic encryption
Sentiment analysis over encrypted data
Titanic Competition with Privacy Preserving Machine Learning
Work with encrypted DataFrames using Concrete ML
Train a linear classifier on encrypted data using Concrete ML and Fully Homomorphic Encryption (FHE)
How to convert a scikit-learn model into its homomorphic equivalent
Click here