Skip to main content

Contributors Forks Stargazers Issues Apache License


Logo

BlindAI

Website Blog LinkedIn

BlindAI is an AI privacy solution, allowing users to query popular AI models or serve their own models whilst ensuring that users' data remains private every step of the way.

Explore the docs »

Try Demo · Report Bug · Request Feature

Table of Contents
  1. About The Project
  2. Getting Started
  3. Usage
  4. Getting Help
  5. License
  6. Contact

🔒 About The Project

BlindAI is an open-source solution to query and deploy AI models while guaranteeing data privacy. The querying of models is done via our easy-to-use Python library.

Data sent by users to the AI model is kept confidential at all times by hardware-enforced Trusted Execution Environments. We explain how they keep data and models safe in detail here.

There are two main scenarios for BlindAI:

  • BlindAI API: Using BlindAI to query popular AI models hosted by Mithril Security.
  • BlindAI Core: Using BlindAI's underlying technology to host your own BlindAI server instance to securely deploy your own models.

You can find our more about BlindAI API and BlindAI Core here.

Built With

Rust Python Intel-SGX Tract

(back to top)

🚀 Getting Started

We strongly recommend for you to get started with our Quick tour to discover BlindAI with the open-source model Whisper.

But here’s a taste of what using BlindAI could look like 🍒

BlindAI API

transcript = blindai.api.Audio.transcribe(
    file="patient_104678.wav"
)
print(transcript)

The patient is a 55-year old male with known coronary artery disease.

BlindAI.Core

AI company's side: uploading and deleting models

An AI company AI company want to provide their model as an an easy-to-use service. They upload it to the server, which is assigned a model ID.

response = client_1.upload_model(model="./COVID-Net-CXR-2.onnx")
MODEL_ID = response.model_id
print(MODEL_ID)

8afcdab8-209e-4b93-9403-f3ea2dc0c3ae

When collaborating with clients is done, the AI company can delete their model from the server.

# AI company deletes model after use
client_1.delete_model(MODEL_ID)

Client's side: running a model on confidential data

The client wants to feed their confidential data to the model while protecting it from third-party access. They connect and run the model on the following confidential image.

pos_ret = client_2.run_model(MODEL_ID, positive)
print("Probability of Covid for positive image is", pos_ret.output[0].as_flat()[0][1])

Probability of Covid for positive image is 0.890598714351654

For more examples, please refer to the Documentation

(back to top)

🙋 Getting help

📜 License

Distributed under the Apache License, version 2.0. See LICENSE.md for more information.

📇 Contact

Mithril Security - @MithrilSecurity - contact@mithrilsecurity.io

Project Link: https://github.com/mithril-security/blindai

(back to top)

Metadata

Release files for blindai 0.6.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for blindai 0.6.3
File Size Uploaded
blindai-0.6.3.tar.gz 24.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for blindai 0.6.3
File Interpreter ABI Platform
blindai-0.6.3-py3-none-any.whl Python 3 none any Details

Total release size: 49.2 kB

Release files / blindai-0.6.3.tar.gz

Download URL blindai-0.6.3.tar.gz
Size 24.4 kB
Tags Source
SHA-256 checksum
How to use checksums
35b97497218de505cc0ab8eab5a16d9b8ee07756fa012ba705ca0b4bf3461f08
BLAKE2b-256 checksum
How to use checksums
583f38d7319adc2676f16c9f28e2b4f2d86b7962c75e27fdc74147a8bb8970b9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.4.2 CPython/3.10.9 Linux/5.15.0-69-generic

Release files / blindai-0.6.3-py3-none-any.whl

Download URL blindai-0.6.3-py3-none-any.whl
Size 24.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
44d61980504d7924f528d100ac487503e3680504afdcdab655d833c246609c11
BLAKE2b-256 checksum
How to use checksums
0b8ee949eea6ba595b62345eb56d496eb362fc100b719d7de75b99570f4ee20c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.4.2 CPython/3.10.9 Linux/5.15.0-69-generic

Release history Release notifications | RSS feed

This release

0.6.3 This release

2 release files

0.6.2

2 release files

0.6.1

2 release files

0.5.9

5 release files

0.5.8

10 release files

0.5.7

10 release files

0.5.6

10 release files

0.5.4

10 release files

0.5.1

5 release files

0.5.0

5 release files

0.3.1

15 release files

0.3.0

5 release files

0.2.0

5 release files

0.1.1

5 release files

0.1.0

5 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page