Learn

Start with what a trusted execution environment (TEE) protects and what its attestation report shows, then compare other ways to check a claim. Each guide turns a check into numbered steps with a worksheet.

The TEE path

Read these five articles in order, from what makes a claim checkable to how TEEs compare with other approaches.

  1. 1

    Explainer · 8 min read · verifiable.pro Research, automated.

    What makes an AI system verifiable?

    After this you can separate a provider's claim from the evidence that could support it, and name what a check leaves to trust.

  2. 2

    Explainer · 8 min read · verifiable.pro Research, automated.

    Remote attestation for AI workloads, explained

    After this you can name the attester, verifier and relying party in an AI service, and say what a valid report leaves open.

  3. 3

    Guide · 9 min read · verifiable.pro Research, automated.

    How to read a remote attestation report

    After this you can check a report's signature chain, firmware versions, measurements, freshness and connection binding before sending data.

  4. 4

    Analysis · 9 min read · verifiable.pro Research, automated.

    Private AI Compute Services: What the Published Designs Let Outsiders Check

    After this you can compare what Apple, Meta, Google and Cohere let outsiders check about the software that handles requests.

  5. 5

    Analysis · 8 min read · verifiable.pro Research, automated.

    Three Ways to Check an AI Answer: Proofs, Enclaves and Re-execution Compared

    After this you can decide when a TEE's evidence is enough and when to add re-execution or a proof.

  6. Planned CPU TEEs compared: Intel TDX, AMD SEV-SNP and Arm CCA

  7. Planned GPU confidential computing for AI inference

  8. Planned How TEEs fail: physical, side-channel and configuration attacks

Run a check yourself

  • Guide · 8 min read · verifiable.pro Research, automated.

    How to verify a signed model before you load it

    Before any code loads the weights, use this five-step worksheet to check that a model's files are the ones the expected publisher signed, and to record which files the check covered.

    You need: the model files, the signature bundle and the expected signer's identity

    5 steps

  • Guide · 9 min read · verifiable.pro Research, automated.

    Checklist: evaluating a verifiable inference claim

    Ten checks to run when a provider or protocol says its model outputs can be verified. Each comes with a worksheet for recording what the evidence covers and what you still have to trust.

    You need: the written claim, the paper or specification behind it, and the verification tools

    10 steps

  • Guide · 9 min read · verifiable.pro Research, automated.

    How to check a Content Credential, and what it does not show

    Before you publish or cite an image or video, use this six-step worksheet to decide what its C2PA manifest establishes: who signed which claims, and which bytes those claims cover.

    You need: the file as you received it, a C2PA validator and the C2PA trust lists

    6 steps

Terms to know first

Trusted execution environment (TEE)可信执行环境(TEE)
A hardware-isolated environment for running code, such as an enclave or a confidential VM. It is designed to keep the code and data inside it confidential and unmodified, even if the operating system, the hypervisor or the cloud operator is compromised.
Remote attestation远程证明
A process in which a device produces signed evidence about its hardware and software state. A verifier checks the evidence, and a relying party uses the result to decide whether to trust the device.
Measurement度量值
A cryptographic hash (a digital fingerprint) of code, firmware or configuration. The hash is recorded when the item is loaded, and attestation evidence reports it.
Reference value参考值
An expected value, such as the measurement of an approved software release, that a verifier compares with the claims in attestation evidence.
Verifier (attestation)验证方(远程证明)
In remote attestation, the party that checks an attester's evidence against reference values, endorsements and policy, and produces an attestation result.
Relying party依赖方
In remote attestation, the party that uses attestation results to decide whether to trust a device, for example before sending it data or releasing a key.
Freshness新鲜性
Assurance that attestation evidence is recent enough to reflect the attester's current state. To establish freshness, the signed evidence usually includes a nonce (an unpredictable value that the verifier chooses) or a trusted timestamp.
Trusted computing base (TCB)可信计算基(TCB)
All the hardware, firmware and software that must work correctly for a system's security policy to be enforced.

Full glossary

All explainers and guides

  1. What makes an AI system verifiable?
  2. How to verify a signed model before you load it
  3. Remote attestation for AI workloads, explained
  4. How to read a remote attestation report
  5. Checklist: evaluating a verifiable inference claim
  6. How to check a Content Credential, and what it does not show