Consortium forVerified Computing

K-0005

Root of trust

A component that anchors security functions such as measurement, storage and reporting, and must be trusted because its misbehaviour cannot be detected.

Source reviewed 2026-09-25

01 / The mechanism and its boundary

What is being described

A root of trust is a hardware, firmware or software element that forms the basis of security functions such as measurement, storage, reporting, recovery, verification and update, and that must always behave as expected because its misbehaviour cannot be detected S-1601 S-1600.

It is typically the first element in a chain of trust and anchors more complex functions built on it S-1601. Because it is trusted by assumption, it must be secure by design S-1600. The Trusted Computing Group distinguishes a root of trust for measurement, which makes the first integrity measurement and adds it to a tamper-resistant log, from a root of trust for reporting, which vouches for platform characteristics during remote attestation S-1602. Shavit's framework needs hardware roots of trust on ML chips, and calls for open-source designs so that independent verifiers can check them for backdoors S-0029. A 2026 MIRI Technical Governance Team post on TEE-based attestation calls key provenance the most difficult part of TEE hardware to accept, because a few hardware vendors generated the keys and fused them onto the chips, and whoever holds a hardware key or can certify one can in principle produce valid attestation reports S-0014.

Connections in the research map

Related research

mechanism / R1

Chip location verification

Timing a chip's signed replies to trusted servers at known places, so that the speed of light bounds how far away the chip can be.

mechanism / R2

Confidential multi-party verification

Lets mutually distrusting parties run an agreed check over private models or records inside attested enclaves or zero-knowledge proofs, revealing only the result.

mechanism / R2

Safeguard attestation

Hardware-signed evidence that an AI service ran its declared safeguards, such as a guardrail classifier or monitor, when producing a given response.

mechanism / R3

TEE remote attestation for AI workloads

Trusted execution environments (TEEs) in CPUs and GPUs sign reports of loaded software, so a remote party can check which code ran an AI workload.

implementation / R3

Apple Private Cloud Compute

Apple's cloud AI inference service, in which user devices send requests only to servers that attest to running software published in a public transparency log.

implementation / R1

Lucid sovereignty (location) certificates

A draft specification, hosted by Lucid Computing, for short-lived certificates that bound where a workload runs by timing signed exchanges with fixed anchors.

implementation / R3

Tinfoil model identity (Modelwrap)

Tinfoil's method for proving which model weights its enclave-hosted inference service runs, by binding a dm-verity hash of the weights into remote attestation.

Sources and provenance

  1. S-1601 / Tier A

    Platform Firmware Resiliency Guidelines (NIST SP 800-193) ↗

    A. Regenscheid · 2018 · National Institute of Standards and Technology

    Supports: definition of RoT and its security-specific functions; must always behave as expected because its misbehaviour cannot be detected; first element of a chain of trust anchoring more complex functionality

    Locator: §3.3, pp. 11–12

    Version and catalogue details
  2. S-1600 / Tier A

    NIST Computer Security Resource Center (CSRC) Glossary ↗

    National Institute of Standards and Technology · 2026 · NIST Computer Security Resource Center

    Supports: roots of trust as highly reliable hardware, firmware and software components that must be secure by design

    Locator: term: roots_of_trust (NIST SP 800-172r3; NISTIR 8320)

    Version and catalogue details
  3. S-1602 / Tier B

    TCG Glossary ↗

    Trusted Computing Group · 2017 · Trusted Computing Group

    Supports: RTM and RTR definitions

    Locator: p. 9

    Version and catalogue details
  4. S-0029 / Tier B

    What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring ↗

    Y. Shavit · 2023 · arXiv

    Supports: hardware roots of trust on ML chips; open-source RoT designs so verifiers can check for backdoors

    Locator: §6.2

    Version and catalogue details
  5. S-0014 / Tier C

    On TEEs for Privacy-Preserving Monitoring in AI Governance ↗

    Gloria Z · 2026 · MIRI Technical Governance Team

    Supports: key provenance as the most difficult part of TEE hardware to accept; vendors generate and fuse keys; holder or certifier of a hardware key can produce valid attestation reports

    Locator: Limitations

    Version and catalogue details
Source review date
2026-09-25
Drafted by (source map)
ai
Review handles (source map)
codex-review