Skip to content

👋 Welcome to BlindLlama!

Making AI Confidential & Transparent

📜 What is BlindLlama?

Introduction

🛠️ BlindLlama make AI Confidential and Transparent by ensuring users' data is never exposed, thanks to end-to-end protection with secure hardware.

🔐 To guarantee that data sent to the inference server remains protected, we have developed a Confidential and Transparent architecture to serve AI models.

Our backend has two key properties:

  • Confidentiality: Data is never accessible. The AI models are served inside hardened environments that do not expose data even to the AI provider. All points of access, such as SSH, logs, networks, etc., are blocked to ensure the isolation of data.

  • Transparency: We provide verifiable cryptographic proof that these controls are in place, thanks to the use of Trusted Platform Modules (TPMs).

Warning

BlindLlama is still under development. It does not yet have the full security features.

Do not test it with confidential information... yet!

We welcome contributions to our project from the community! Don't hesitate to raise issues on GitHub, reach out to us or see our guide on how to audit BlindLlama (coming soon!).

👩🏻‍💻 Use cases

Several scenarios can be answered by using BlindLlama, such as:

  • Benchmarking the best open-source LLMs against one’s private data to find out which one is the most relevant without having to do any provisioning
  • Structuring medical documents
  • Analysis or auto-completion of a confidential code base

✅ When should you use BlindLlama?

  • You don’t want to expose data, even to admins

❌ What is not covered by BlindLlama?

  • BlindLlama’s trust model implies some level of trust in Cloud providers and hardware providers since we leverage secure hardware available and managed by Cloud providers (see our trust model section for more details).

BlindLlama virtually provides the same level of security, privacy, and control as solutions provided by Cloud providers like Azure OpenAI Services.

🚀 Getting started

📚 Advanced security whitepaper

We created the BlindLlama whitepaper to cover the architecture and security features behind BlindLLama in greater detail.

The whitepaper is intended for an audience with security expertise.

You can read or download the whitepaper here!

📇 Get in touch

We would love to hear your feedback or suggestions, here are the ways you can reach us:

Want to hear more about our work on privacy in the field AI?

  • Check out our blog
  • Subscribe to our newsletter here

Thank you for your support!

🔒 Who made BlindLlama?

BlindLlama is developed by Mithril Security, a startup focused on democratizing privacy-friendly AI using secure hardware solutions.

We have already had our first project, BlindAI, an open-source Rust inference server that deploys ONNX models on Intel SGX secure enclaves, audited by Quarkslab.

BlindLlama builds on the foundations of BlindAI but provides much faster performance and focuses on serving managed models directly to developers instead of helping AI engineers to deploy models.