Skip to content

Exploration of secure hardware solutions for safe AI deployment

This collaboration between the Future of Life Institute and Mithril Security explores hardware-backed AI governance tools for transparency, traceability, and confidentiality.
November 30, 2023
Future of Life Institute



AI safety has become a key subject with the recent progress of AI. Debates on the topic have helped outline desirable properties a safe AI should follow, such as provenance (where does the model come from), confidentiality (how to ensure the confidentiality of prompts or of the model weights), or transparency (how to know what model is used on data).

While such discussions have been necessary to define what properties such models should have, they are not sufficient, as there are few technical solutions to actually guarantee that those properties are implemented in production. 

For instance, there is no way to guarantee that a good actor who trained an  AI satisfying some safety requirements has actually deployed that same model, nor is it possible to detect if a malicious actor is serving a harmful model. This is due to the lack of transparency and technical proof that a specific and trustworthy model is indeed loaded in the backend.

This need for technical answers to the AI governance challenges has been expressed in the highest spheres. For instance, the White House Executive Order on AI Safety and Security has highlighted the need to develop privacy-preserving technologies and the importance of having confidential, transparent, and traceable AI systems.

Hardware-backed security today

Fortunately, modern techniques in cryptography and secure hardware technology provide the building blocks to provide verifiable systems that can enforce AI governance policies. For example, unfalsifiable cryptographic proof can be created to attest that a model comes from the application of a specific code on a specific dataset. This could prevent copyright issues, or prove that a certain number of training epochs were done, verifying whether a threshold in compute has or has not been breached. 

The field of secure hardware has been evolving and has reached a stage where it can be used in production to make AI safer. While initially developed for users’ devices (e.g. iPhones use secure enclaves to securely store and process biometric data), large server-side processors have become mature enough to tackle AI workloads.

While recent cutting-edge AI hardware, such as Intel Xeon with Intel SGX or Nvidia H100s with Confidential Computing, possess the hardware features to implement AI governance properties, few projects have emerged yet to leverage them to build AI governance tooling.

Proof-of-concept: Secure AI deployment

The Future of Life Institute, an NGO leading the charge for safety in AI systems, has partnered with Mithril Security, a startup pioneering the use of secure hardware with enclave-based solutions for trustworthy AI. This collaboration aims to demonstrate how AI governance policies can be enforced with cryptographic guarantees.

In our first joint project, we created a proof-of-concept demonstration of confidential inference

Scenario: Leasing of confidential and high-value AI model to untrusted party

The use case we are interested in involves two parties: 

  • an AI custodian with a powerful AI model
  • an AI borrower who wants to consume the model on their infrastructure but is not to be trusted with the weights directly

The AI custodian wants technical guarantees that:

  • the model weights are not directly accessible to the AI borrower
  • trustable telemetry is provided to know how much computing is being done
  • a non-removable off-switch button can be used to shut down inference if necessary

Current AI deployment solutions, where the model is shipped on the AI borrower infrastructure, provide no IP protection, and it is trivial for the AI borrower to extract the weights without awareness from the custodian. 

Through this collaboration, we have developed a framework for packaging and deploying models in an enclave using Intel secure hardware. This enables the AI custodian to lease a model, deployed on the infrastructure of the AI borrower, while having hardware guarantees the weights are protected and the trustable telemetry for consumption and off-switch will be enforced.

While this proof-of-concept is not necessarily deployable as is, due to performance (we used Intel CPUs) and specific hardware attacks that need mitigation, it serves as a demonstrator of how enclaves can enable collaboration under agreed terms between parties with potentially misaligned interests. 

By building upon this work, one can imagine how a country like the US could lease its advanced AI models to allied countries while ensuring the model’s IP is protected and the ally’s data remains confidential.

Open-source deliverables available

This proof of concept is made open-source under an Apache-2.0 license. It is based on BlindAI, an open-source secure AI deployment solution using Intel SGX, audited by Quarkslab

We provide the following resources to explore in more detail our collaboration on hardware-backed AI governance:

  • A demo to understand how controlled AI consumption works and looks like in practice. 
  • Code is made open-source to reproduce our results.
  • Technical documentation to dig into the specifics of the implementation.

Future investigations

By developing and evaluating frameworks for hardware-backed AI governance, FLI and Mithril hope to help encourage the creation and use of such measures so that we can keep AI safe without compromising the interests of AI providers, users, or regulators.

Many other capabilities are possible, and we plan to roll out demos and analyses of more in the coming months.

Many of these can be implemented on existing and widely deployed hardware to allow AI compute governance backed by hardware measures. This answers concerns that compute governance mechanisms are unenforceable or enforceable only with intrusive surveillance.

The security of these measures needs testing and improvement for some scenarios, and we hope these demonstrations, and the utility of hardware-backed AI governance, will encourage both chipmakers and policymakers to include more and better versions of such security measures in upcoming hardware.

Future of Life Institute
Mithril Security
This content was first published at on November 30, 2023.

About the Future of Life Institute

The Future of Life Institute (FLI) is a global non-profit with a team of 20+ full-time staff operating across the US and Europe. FLI has been working to steer the development of transformative technologies towards benefitting life and away from extreme large-scale risks since its founding in 2014. Find out more about our mission or explore our work.

Our content

Related content

Other posts about 

If you enjoyed this content, you also might also be interested in:

Disrupting the Deepfake Pipeline in Europe

Leveraging corporate criminal liability under the Violence Against Women Directive to safeguard against pornographic deepfake exploitation.
February 22, 2024

Realising Aspirational Futures – New FLI Grants Opportunities

Our Futures Program, launched in 2023, aims to guide humanity towards the beneficial outcomes made possible by transformative technologies. This year, as […]
February 14, 2024

Protect the EU AI Act

A last-ditch assault on the EU AI Act threatens to jeopardise one of the legislation's most important functions: preventing our most powerful AI models from causing widespread harm to society.
November 22, 2023

Miles Apart: Comparing key AI Act proposals

Our analysis shows that the recent non-paper drafted by Italy, France, and Germany largely fails to provide any provisions on foundation models or general purpose AI systems, and offers much less oversight and enforcement than the existing alternatives.
November 21, 2023

Some of our projects

See some of the projects we are working on in this area:

Mitigating the Risks of AI Integration in Nuclear Launch

Avoiding nuclear war is in the national security interest of all nations. We pursue a range of initiatives to reduce this risk. Our current focus is on mitigating the emerging risk of AI integration into nuclear command, control and communication.
September 29, 2023

Strengthening the European AI Act

Our key recommendations include broadening the Act’s scope to regulate general purpose systems and extending the definition of prohibited manipulation to include any type of manipulatory technique, and manipulation that causes societal harm.
September 7, 2023

Sign up for the Future of Life Institute newsletter

Join 40,000+ others receiving periodic updates on our work and cause areas.
cloudmagnifiercrossarrow-up linkedin facebook pinterest youtube rss twitter instagram facebook-blank rss-blank linkedin-blank pinterest youtube twitter instagram