aicert.mithrilsecurity.io Open in urlscan Pro
2606:4700::6811:2152  Public Scan

Form analysis
3 forms found in the DOM

<form class="md-header__option" data-md-component="palette">
  <input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="" data-md-color-accent="" aria-label="" type="radio" name="__palette" id="__palette_1">
  <label class="md-header__button md-icon" title="" for="__palette_2">
    <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
      <path
        d="M12 7a5 5 0 0 1 5 5 5 5 0 0 1-5 5 5 5 0 0 1-5-5 5 5 0 0 1 5-5m0 2a3 3 0 0 0-3 3 3 3 0 0 0 3 3 3 3 0 0 0 3-3 3 3 0 0 0-3-3m0-7 2.39 3.42C13.65 5.15 12.84 5 12 5c-.84 0-1.65.15-2.39.42L12 2M3.34 7l4.16-.35A7.2 7.2 0 0 0 5.94 8.5c-.44.74-.69 1.5-.83 2.29L3.34 7m.02 10 1.76-3.77a7.131 7.131 0 0 0 2.38 4.14L3.36 17M20.65 7l-1.77 3.79a7.023 7.023 0 0 0-2.38-4.15l4.15.36m-.01 10-4.14.36c.59-.51 1.12-1.14 1.54-1.86.42-.73.69-1.5.83-2.29L20.64 17M12 22l-2.41-3.44c.74.27 1.55.44 2.41.44.82 0 1.63-.17 2.37-.44L12 22Z">
      </path>
    </svg>
  </label>
  <input class="md-option" data-md-color-media="" data-md-color-scheme="default" data-md-color-primary="" data-md-color-accent="" aria-label="" type="radio" name="__palette" id="__palette_2">
  <label class="md-header__button md-icon" title="" for="__palette_1" hidden="">
    <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
      <path
        d="m17.75 4.09-2.53 1.94.91 3.06-2.63-1.81-2.63 1.81.91-3.06-2.53-1.94L12.44 4l1.06-3 1.06 3 3.19.09m3.5 6.91-1.64 1.25.59 1.98-1.7-1.17-1.7 1.17.59-1.98L15.75 11l2.06-.05L18.5 9l.69 1.95 2.06.05m-2.28 4.95c.83-.08 1.72 1.1 1.19 1.85-.32.45-.66.87-1.08 1.27C15.17 23 8.84 23 4.94 19.07c-3.91-3.9-3.91-10.24 0-14.14.4-.4.82-.76 1.27-1.08.75-.53 1.93.36 1.85 1.19-.27 2.86.69 5.83 2.89 8.02a9.96 9.96 0 0 0 8.02 2.89m-1.64 2.02a12.08 12.08 0 0 1-7.8-3.47c-2.17-2.19-3.33-5-3.49-7.82-2.81 3.14-2.7 7.96.31 10.98 3.02 3.01 7.84 3.12 10.98.31Z">
      </path>
    </svg>
  </label>
</form>

Name: search —

<form class="md-search__form" name="search">
  <input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required="">
  <label class="md-search__icon md-icon" for="__search">
    <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
      <path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"></path>
    </svg>
    <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
      <path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"></path>
    </svg>
  </label>
  <nav class="md-search__options" aria-label="Search">
    <button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
      <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
        <path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z"></path>
      </svg>
    </button>
  </nav>
</form>

GET //readthedocs.org/projects/aicert/search/

<form id="flyout-search-form" class="wy-form" target="_blank" action="//readthedocs.org/projects/aicert/search/" method="get">
  <input type="text" name="q" aria-label="Dokumente durchsuchen" placeholder="Dokumente durchsuchen">
</form>

Text Content

Skip to content

AICert
🏠 Overview

Type to start searching
mithril-security/aicert
 * 1
 * 0

AICert
mithril-security/aicert
 * 1
 * 0

 * 🏠 Overview 🏠 Overview
   Table of contents
    * 📜 What is AICert?
       * ✅ Use cases
   
    * 🔍 Features
    * 🚀 Getting started
    * ⚠️ Limitations
    * 🙋 Getting help
    * 🔒 Who made AICert?

 * 🚀 Getting Started
   🚀 Getting Started
    * Getting started
    * How we attest AI
    * Technology overview

Table of contents
 * 📜 What is AICert?
    * ✅ Use cases

 * 🔍 Features
 * 🚀 Getting started
 * ⚠️ Limitations
 * 🙋 Getting help
 * 🔒 Who made AICert?


👋 WELCOME TO AICERT!

--------------------------------------------------------------------------------

Making AI Traceable and Transparent


📜 WHAT IS AICERT?

--------------------------------------------------------------------------------

🛠️ AICert aims to make AI traceable and transparent by enabling AI builders to
create certificates with cryptographic proofs binding the weights to the
training data and code. AI builders can be foundational model providers or
companies that finetune the foundational models to their needs.

👩‍💻 End users are the final consumers of the AI builders’ models. They can
then verify these AI certificates to have proof that the model they talk to
comes from a specific training set and code, and therefore alleviates copyright,
security and safety issues.

🔐 We leverage Trusted Platform Modules (TPMs) in order to attest the whole
stack used for producing the model, from the UEFI, all the way to the code and
data, through the OS.

Measuring the software stack, training code and inputs and binding them to the
final weights allows the derivation of certificates that contain irrefutable
proof of model provenance.


✅ USE CASES

AICert addresses some of the most urgent concerns related to AI provenance. It
allows AI builders to:

 * Prove their AI model was not trained on copyrighted, biased or non-consensual
   PII data
 * Provide an AI Bill of Material about the data and code used, which makes it
   harder to poison the model by injecting backdoors in the weights
 * Provide a strong audit trail with irrefutable proof for compliance and
   transparency

Warning

AICert is still under development. Do not use it in production!

If you want to contribute to this project, do not hesitate to raise an issue.


🔍 FEATURES

--------------------------------------------------------------------------------

 * AI model traceability: create AI model ID cards that provide cryptographic
   proof binding model weights to a specific training set and code
 * Non-forgeable proofs: leverage TPMs to ensure non-forgeable AI model ID cards
 * Flexible training: use your preferred tooling for training
 * No slowdown induced during training
 * Azure support

Coming soon:

 * Benchmark linking: provide cryptographic binding of model weights to specific
   benchmarks that were run for this specific model
 * Multi-Cloud support with AWS and GCP coverage
 * Single and multi-GPU support


🚀 GETTING STARTED

--------------------------------------------------------------------------------

 * Check out our “Getting started guide”, which will walk you through an
   example!
 * Discover how we bind model weights to training inputs and code
 * Learn more about the AICert architecture & workflow


⚠️ LIMITATIONS

--------------------------------------------------------------------------------

While we provide traceability and ensure that a given set of weights comes from
applying a specific training code on a specific dataset, there are still
challenges to solve:

 * The training code and data have to be inspected. AICert does not audit the
   code or input data for threats, such as backdoors injected into a model by
   the code or poisonous data. It will simply allow us to prove model
   provenance. It is up to the AI community or end-user to inspect or prove the
   trustworthiness of the code and data.
 * AICert itself has to be inspected, all the way from the OS we choose to the
   HTTP server and the app we provide to run the code on the training data.

We are well aware that AICert is not a silver bullet, as to have a fully
trustworthy process, it requires scrutiny of both our code and the code and data
of the AI builder.

However, by combining both, one can have a solid foundation for the AI supply
chain.


🙋 GETTING HELP

--------------------------------------------------------------------------------

 * Go to our Discord #support channel

 * Book a meeting with us


🔒 WHO MADE AICERT?

--------------------------------------------------------------------------------

AICert was developed by Mithril Security. Mithril Security is a startup focused
on AI privacy solutions based on Confidential Computing technologies. We provide
several open-source tools for querying and deploying AI solutions to improve AI
provider's security posture and compliance.

Next Getting started

Made with Material for MkDocs


  v: latest
Versionen latest readme docs Auf Read the Docs Projektstartseite
Erstellungsprozesse Downloads Auf GitHub Ansehen Bearbeiten Suche


--------------------------------------------------------------------------------

Bereitgestellt von Read the Docs · Datenschutz-Bestimmungen