π Welcome to BlindAI!
An AI privacy solution to query models, while ensuring your data remains confidential every step of the way!
What is BlindAI?
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.
BlindAi consists of:
-
BlindAI API: for querying popular AI models hosted by Mithril Security (with BlindAI Core running under the hood). Its a Python library π.
-
BlindAI Core: for hosting your own BlindAI server instance in order to securely deploy your own models. It comes in two parts: a privacy-friendly server coded in Rust π¦ using Intel SGX (Intel Software Guard Extensions) π and AWS Nitro Enclaves πͺοΈ to ensure your data stays safe and an easy-to-use Python client SDK π.
You can find our more about BlindAI and BlindAI.Core here.
You can check out the code on our GitHub.
Weβll update the documentation as new features come in, so dive in!
Getting started
- Follow our βQuick tourβ tutorial
- Tackle the technologies we use to ensure privacy
- Discover the differences between BlindAI and BlindAI Core
Getting help
- Go to our Discord #support channel
- Report bugs by opening an issue on our BlindAI Github
- Book a meeting with us
How is the documentation structured?
-
Tutorials take you by the hand to install and run BlindAI. We recommend you start with the Quick tour and then move on to the other tutorials!
-
Concepts guides discuss key topics and concepts at a high level. They provide useful background information and explanations, especially on cybersecurity.
-
How-to guides are recipes. They guide you through the steps involved in addressing key problems and use cases. They are more advanced than tutorials and assume some knowledge of how BlindAI works.
-
API Reference contains technical references for BlindAIβs API machinery. They describe how it works and how to use it but assume you have a good understanding of key concepts.
-
Security guides contain technical information for security engineers. They explain the threat models and other cybersecurity topics required to audit BlindAI's security standards.
-
Advanced guides are destined to developers wanting to dive deep into BlindAI and eventually collaborate with us to the open-source code.
Who made BlindAI?
BlindAI was developed by Mithril Security. Mithril Security is a startup focused on confidential machine learning based on Confidential Computing technology. We provide open-source privacy solutions to query and deploy AI models while guaranteeing data privacy.