# AI verification proposal

A proposal built with the Proposal Explorer of the AI Verification Tech Map (https://trustbutveri.fyi/), from its records of 2026-10-08. Interactive version: https://trustbutveri.fyi/explorer/?mechanisms=M-0014,M-0012&implementations=M-0014:I-0010

How to read it: a claim is something one party wants to verify about another's AI hardware or software. A mechanism is a general technique for verifying claims; it is "aimed at" a claim when that is its direct purpose, and "supporting" when it contributes without being aimed at it. A claim is addressed when a mechanism in the proposal is aimed at it and is not excluded by the filters; addressed does not mean verified, so check that mechanism's readiness and open flaws. Readiness levels R0 to R4 describe one record's public evidence for its assessed use and are never combined. Definitions: https://trustbutveri.fyi/about/methodology/ (roles, properties and flaws) and https://trustbutveri.fyi/about/readiness/ (readiness levels).

## Filters

Filters apply to mechanisms only and describe the setting the proposal is for.

None set. Every mechanism on the map was available.

## Overview

One row per mechanism, read from its record. Open flaws: critical / significant / minor. The last three columns are the editors' reading of what the verifier sees.

| Mechanism | Readiness | Prover | Attack testing | Hardware | Open flaws | Weights | Inputs and outputs | Training data |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Bandwidth limits and compartmentalization / RAND secure inference data center (SIDC) design | R1 | Semi-trusted | Analysis | Retrofit device | 0 / 1 / 1 | unspecified | unspecified | unspecified |
| Model identity attestation | R3 | Semi-trusted | Independent red-team | Existing features | 1 / 2 / 0 | depends | depends | not involved |

## Claims

No claims chosen.

## Mechanisms

### Bandwidth limits and compartmentalization

A RAND design for a purpose-built facility that serves already-trained AI models while protecting weights and inference data against state-level attackers. ([Bandwidth limits and compartmentalization](https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/))

- Assessment: selected implementation [RAND secure inference data center (SIDC) design](https://trustbutveri.fyi/implementations/rand-secure-inference-data-centers/).
- Readiness: R1 Proposed, assessed for the operator's own weight security, with no outside verification described.
- Claims in this proposal: none of them.
- Threat model: semi-trusted prover. Hardware: retrofit device. Prover cooperation: required. Attack testing: analysis. Category: Isolation & system architectures.
- What the verifier sees: model weights unspecified; inputs and outputs unspecified; training data unspecified. This Explorer has no asset-specific exposure assessment for this implementation. Check its source and deployment assumptions.

### Model identity attestation

Establishes that responses come from a specific, committed set of model weights, using enclave measurements or recomputation of sampled outputs. ([Model identity attestation](https://trustbutveri.fyi/mechanisms/model-identity-attestation/))

- Assessment: mechanism family.
- Readiness: R3 In production, assessed for showing users that a service runs the declared model weights.
- Claims in this proposal: none of them.
- Threat model: semi-trusted prover. Hardware: existing features. Prover cooperation: required. Attack testing: independent red-team. Category: Cryptographic & computational.
- What the verifier sees: model weights depends; inputs and outputs depends; training data not involved. The enclave route shows only hashes; the recomputation route gives the verifier the weights and the sampled requests and responses.


## Properties

**In production**

- Model identity attestation: R3 In production, assessed for showing users that a service runs the declared model weights

**No new hardware needed**

- Model identity attestation

**Flaws since mitigated**

- Launch-state attestation does not by itself cover weights loaded later (in Model identity attestation) [6][18]


## Attack testing

Published attempts to break a system, including those that found failures. Testing history does not establish that open flaws are resolved.

**Testing history**

- Bandwidth limits and compartmentalization / RAND secure inference data center (SIDC) design: Analysis
- Model identity attestation: Independent red-team


## Limits

**Open critical flaws**

- Underlying attestation can be forged or relayed (demonstrated attack, in Model identity attestation; https://trustbutveri.fyi/mechanisms/model-identity-attestation/#flaw-1) [7][9][13][15][16][17]. Inherited finding. Critical for the enclave route against an operator with physical access to affected hardware, or control of an unpatched SEV-SNP hypervisor. It does not apply to the recomputation route. PAL*M excludes physical attacks, and Tinfoil acknowledges this boundary. The enclave route inherits the platform-specific TEE attestation failures. Intel TDX forgery and H100 relay were demonstrated with physical access and host control. Battering RAM defeated AMD SEV-SNP attestation on DDR4 servers; RMPocalypse did so from malicious host software on platforms without AMD's fixes. These demonstrate failures of the trust roots, not of each model-commitment protocol. Related finding: https://trustbutveri.fyi/mechanisms/tee-remote-attestation/#flaw-1.

  Response: The TEE.fail authors report that physical interposer attacks are outside Intel's and AMD's threat models. AMD reports fixes for RMPocalypse.

  Related mechanism: Hardware-enabled guarantees (flexHEG) and guarantee processors (R1, not in the proposal). A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically.

**Open significant flaws**

- Everything rests on the trusted setup (theoretical argument, in RAND secure inference data center (SIDC) design; https://trustbutveri.fyi/implementations/rand-secure-inference-data-centers/#flaw-1) [1]. Reference measurements for model weights and reference data are established in a trusted setup phase. The report states that the system cannot detect compromise that happened before ingestion if the trusted setup itself is compromised.
- For private models, a user can confirm consistency but not content (open question, in Model identity attestation; https://trustbutveri.fyi/mechanisms/model-identity-attestation/#flaw-3) [6][19]. When weights are not published, users can check that the same root hash is served each time, but not what the model is. Pairing the hash with an attested evaluation, as in Attestable Audits, is one proposed remedy.
- Recomputation depends on trusted logging and randomness, and its tolerance leaves a covert channel (demonstrated attack, in Model identity attestation; https://trustbutveri.fyi/mechanisms/model-identity-attestation/#flaw-4) [8][14]. The recomputation variant assumes that every input, output and seed is logged correctly, and that the attacker can neither predict nor manipulate which messages are sampled for verification. Legitimate nondeterminism concentrates at a few token positions, and slow leaks within the tolerated slack remain possible. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token, reducing the exfiltration slowdown from 146–254 times under benign prompts to 60–118 times. The attack targets the exfiltration bound, not the check that outputs match the declared model.

  Related mechanism: Network taps and certifiers (R1, not in the proposal). Taps are proposed to copy and hash traffic on the monitored links, reducing reliance on the prover's own log. This still depends on the monitored boundary and trusted capture.

  Related mechanism: Deterministic and bit-exact inference (R3, not in the proposal). Bit-exact inference would remove the numerical tolerance that leaves this channel.

**Family finding context**

- Context for RAND secure inference data center (SIDC) design; applicability depends on the finding's scope. Low-communication training reduces the bandwidth training needs (theoretical argument, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-1) [2][3][4]. DiLoCo matched fully synchronous training on 8 workers while communicating 500 times less. Rahman writes that this family of methods theoretically allows large-scale training with less than 100 Mbps. Lucid includes these methods in its bounds, but notes that extreme activation compression, architectures with unusually small inter-layer widths, or modular paradigms could erode the margin.
- Context for RAND secure inference data center (SIDC) design; applicability depends on the finding's scope. Operator control of pod routing collapses the bound (theoretical argument, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-2) [4]. Lucid's analysis finds that if the operator can freely assign pods to routers, it could dedicate a whole cell of 100 or more pods to one pipeline stage. The bound then falls to about 90–220x uncompressed and as low as about 25x with compression. The proposed mitigation, auditor-controlled random assignment that is periodically re-randomized, has not been implemented.
- Context for RAND secure inference data center (SIDC) design; applicability depends on the finding's scope. Undeclared local storage raises per-pod capacity (theoretical argument, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-3) [4]. More memory or storage per pod helps an adversary. Lucid requires per-pod storage to be declared, capped and physically inspected.
- Context for RAND secure inference data center (SIDC) design; applicability depends on the finding's scope. Training within one pod is not covered (open question, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-4) [4]. Lucid's bounds concern pre-training models larger than the pods are sized for. Training models that fit in one pod, fine-tuning and reinforcement-learning post-training within one pod are outside the modelled threat.
- Context for RAND secure inference data center (SIDC) design; applicability depends on the finding's scope. Parallel scale-up switches are hard enforcement points (theoretical argument, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-5) [5]. In GB200 topologies, GPUs reach GPUs in other nodes through NVSwitches without a NIC on the path. Amodo notes that limits are hard to enforce there because many switches work in parallel, so compromising one or two would bypass the limit.

**Open minor flaws**

- Security weakens over long operation (theoretical argument, in RAND secure inference data center (SIDC) design; https://trustbutveri.fyi/implementations/rand-secure-inference-data-centers/#flaw-2) [1]. The authors claim that the facility can withstand attacks at the OC5 level for a five-year operational period. They expect its ability to withstand long OC5 campaigns to become less robust the longer the facility remains in operation.

**Not yet demonstrated**

- Bandwidth limits and compartmentalization: R1 Proposed, assessed for the operator's own weight security, with no outside verification described


## Possible additions

Mechanisms on the map, not in the proposal, that the records connect to an unaddressed or partly addressed claim, an open flaw or a dependency. Pointers, not recommendations: each brings its own readiness level and flaws, and none is claimed to close a flaw.

- **Hardware-enabled guarantees (flexHEG) and guarantee processors** (R1 Proposed, assessed for checking and enforcing training-compute limits on chips, against adversaries up to states)
  - Bears on the open critical flaw "Underlying attestation can be forged or relayed" in Model identity attestation. A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically.
- **Deterministic and bit-exact inference** (R3 In production, assessed for reproducing open-model inference from receipts in Gensyn's information-market service)
  - Bears on the open significant flaw "Recomputation depends on trusted logging and randomness, and its tolerance leaves a covert channel" in Model identity attestation. Bit-exact inference would remove the numerical tolerance that leaves this channel.
  - Model identity attestation waits on it: Numerical nondeterminism limits how tightly recomputation can pin down the model and sampling.
- **Network taps and certifiers** (R1 Proposed, assessed for committing a complete record of cluster traffic, so declared inference can be checked)
  - Bears on the open significant flaw "Recomputation depends on trusted logging and randomness, and its tolerance leaves a covert channel" in Model identity attestation. Taps are proposed to copy and hash traffic on the monitored links, reducing reliance on the prover's own log. This still depends on the monitored boundary and trusted capture.
- **TEE remote attestation for AI workloads** (R3 In production, assessed for showing which software ran to a party that distrusts the operator holding the hardware)
  - Model identity attestation waits on it: Attestation that resists physical attackers, for the enclave variant.


## Dependencies

**Blockers**

- Bandwidth limits and compartmentalization: No prototype exists; RAND recommends prototyping key security features and integration now. (adversarial validation) [1]
- Bandwidth limits and compartmentalization: The report describes internal integrity checks, audit logging and accreditation, but no way for a party outside the operator to verify the facility's properties. (access & governance) [1]
- Bandwidth limits and compartmentalization: Human review of every prompt and response makes each request take three to five minutes, with the review steps as the rate-limiting factor. (performance & compatibility) [1]
- Bandwidth limits and compartmentalization: Detailed design information is withheld from the public report and is to be evaluated privately with stakeholders, which limits independent public scrutiny. (access & governance) [1]
- Model identity attestation: Attestation that resists physical attackers, for the enclave variant. (hardware trust; waits on TEE remote attestation for AI workloads) [13]
- Model identity attestation: Numerical nondeterminism limits how tightly recomputation can pin down the model and sampling. (protocol soundness; waits on Deterministic and bit-exact inference) [8]
- Model identity attestation: The recomputation variant needs the verifier to hold the declared weights. (access & governance) [8]


## What the verifier sees

- Model weights: shown by none; depends on the design for Model identity attestation; hidden by none; not involved in none; unspecified for Bandwidth limits and compartmentalization.
- Inputs and outputs: shown by none; depends on the design for Model identity attestation; hidden by none; not involved in none; unspecified for Bandwidth limits and compartmentalization.
- Training data: shown by none; depends on the design for none; hidden by none; not involved in Model identity attestation; unspecified for Bandwidth limits and compartmentalization.

## Implementations

- Bandwidth limits and compartmentalization: [AI 2040 inference-only verification stack](https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/) (R1, proposed architecture); [RAND secure inference data center (SIDC) design](https://trustbutveri.fyi/implementations/rand-secure-inference-data-centers/) (R1, proposed architecture)
- Model identity attestation: [Attestable Audits](https://trustbutveri.fyi/implementations/attestable-audits/) (R2, research prototype); [PAL*M](https://trustbutveri.fyi/implementations/palm/) (R2, research prototype); [Tinfoil model identity (Modelwrap)](https://trustbutveri.fyi/implementations/tinfoil-model-identity/) (R3, product)

## Sources

1. Highly Secure Inference Data Centers: A Vertically Integrated Strategy for Security Engineering, S. F. Comer et al. (2026). https://www.rand.org/pubs/research_reports/RRA4827-1.html
2. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). https://arxiv.org/abs/2311.08105
3. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). https://arxiv.org/abs/2605.29359
4. Traffic Shaping for Workload Classification, Lucid Computing (2026). https://lucidcomputing.substack.com/p/traffic-shaping-for-workload-classification
5. The Tray as a Bandwidth Boundary, Amodo Design (2026). https://amododesign.com/notes/2026-03-16-dpu-bandwidth-limiter/
6. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). https://tinfoil.sh/blog/2026-02-03-proving-model-identity
7. PAL*M: Property Attestation for Large Generative Models, P. Chantasantitam et al. (2026). https://arxiv.org/abs/2601.16199
8. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). https://arxiv.org/abs/2511.02620
9. A primer on secure enclaves, Tinfoil (2026). https://docs.tinfoil.sh/verification/secure-enclave-primer
10. Backend infrastructure, Tinfoil (2026). https://docs.tinfoil.sh/verification/attestation-architecture
11. How verification works in Tinfoil, Tinfoil (2026). https://docs.tinfoil.sh/verification/verification-in-tinfoil
12. modelwrap: Reproducible dm-verity read-only image of Huggingface models, Tinfoil (2026). https://github.com/tinfoilsh/modelwrap
13. TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition, J. Chuang et al. (2026). https://tee.fail/
14. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). https://arxiv.org/abs/2608.23375
15. Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing, J. De Meulemeester et al. (2026). https://batteringram.eu/
16. RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP, B. Schlüter & S. Shinde (2025). https://rmpocalypse.github.io/
17. SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020), AMD (2025). https://www.amd.com/en/resources/product-security/bulletin/amd-sb-3020.html
18. On TEEs for Privacy-Preserving Monitoring in AI Governance, Gloria Z (2026). https://techgov.intelligence.org/blog/on-tees-for-privacy-preserving-monitoring-in-ai-governance
19. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). https://arxiv.org/abs/2506.23706