# AI verification proposal

A proposal built with the Proposal Explorer of the AI Verification Tech Map (https://trustbutveri.fyi/), from its records of 2026-10-09. Interactive version: https://trustbutveri.fyi/explorer/?mechanisms=M-0023,M-0013&implementations=M-0013:I-0008

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 development status, security evidence and findings. Definitions: https://trustbutveri.fyi/about/methodology/ (roles, properties and findings) and https://trustbutveri.fyi/about/readiness/ (development status).

## 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 failures: critical / significant / minor. The last three columns are the editors' reading of what the verifier sees. Findings are grouped as known failures, scope limitations and open questions. Only known failures count as failures. Counts are an inventory of published findings, not a risk score.

| Mechanism | Development | Security evidence | Prover | Attack testing | Hardware | Open failures | Weights | Inputs and outputs | Training data |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Safeguard attestation | Research demonstration | Published security analysis | Semi-trusted | Analysis | Existing features | 0 / 2 / 0 | depends | depends | not involved |
| Network taps and certifiers / SASH confidential network logger | Proposed | No published adversarial analysis recorded | Semi-trusted | None | Retrofit device | 0 / 0 / 0 | unspecified | unspecified | unspecified |

## Claims

No claims chosen.

## Mechanisms

### Safeguard attestation

Hardware-signed evidence that an AI service sent a given response through its declared safeguard path, such as a wrapper that calls a guardrail classifier. ([Safeguard attestation](https://trustbutveri.fyi/mechanisms/safeguard-attestation/))

- Assessment: mechanism family.
- Development: Research demonstration (legacy code R2), assessed for attesting that a declared safeguard mediated a service's responses.
- Security evidence: Published security analysis. Independent evaluation: unassessed. Formal proof: unassessed. Deployment assurance: unassessed.
- Claims in this proposal: none of them.
- Threat model: semi-trusted prover. Hardware: existing features. Prover cooperation: required. Attack testing: analysis. Category: Cryptographic & computational.
- What the verifier sees: model weights depends; inputs and outputs depends; training data not involved. The enclave route signs hashes of the safeguard, request and response; a low-trust design has the verifier re-run and screen sampled requests itself.

### Network taps and certifiers

An open-source prototype that routes a facility's inference traffic through a logger and re-runs requests on a separate cluster to check the facility serves inference. ([Network taps and certifiers](https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/))

- Assessment: selected implementation [SASH confidential network logger](https://trustbutveri.fyi/implementations/sash-confidential-network-logger/).
- Development: Proposed (legacy code R1), assessed for telling inference from training on a mutually inspected cluster.
- Security evidence: No published adversarial analysis recorded. Independent evaluation: unassessed. Formal proof: unassessed. Deployment assurance: unassessed.
- Claims in this proposal: none of them.
- Threat model: semi-trusted prover. Hardware: retrofit device. Prover cooperation: required. Attack testing: none. Category: Off-chip devices & sensors.
- 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.


## Properties

**No new hardware needed**

- Safeguard attestation


## Attack testing

Attack testing records published testing for this use. It does not by itself show independent review, a formal proof or that a deployed system is secure.

**Testing history**

- Safeguard attestation: Analysis


## Limits

**Open significant failures**

- Components outside the attested boundary (known failure, theoretical argument, in Safeguard attestation; https://trustbutveri.fyi/mechanisms/safeguard-attestation/evidence/flaws/4/) [1][2]. In the proof-of-guardrail experiments, the guardrail model and the agent's backend model were both reached through external APIs, and the authors leave the decision to trust those APIs to the verifier. The measured wrapper must also have no vulnerability that lets the unmeasured agent bypass the guardrail, for example by executing arbitrary commands inside the enclave. The code's README states that the enclave does not currently restrict the agent's arbitrary command execution, which could be used to bypass guardrails.
- Memory-bus interposition extracts attestation keys and forges attestations (known failure, demonstrated attack, in Safeguard attestation; https://trustbutveri.fyi/mechanisms/safeguard-attestation/evidence/flaws/5/) [1][4][7][8][9][10][11][12][13]. Inherited finding. Applies to variants using the affected Intel or AMD trust roots. PAL*M excludes physical attacks. A TDX-backed safeguard claim against a physical host attacker would be defeated, but these studies do not demonstrate a break of the AWS Nitro proof-of-guardrail prototype or of verifier-side recomputation. The TEE findings cover DDR5 attacks on Intel TDX, the H100 relay demonstration, DDR4 attacks on AMD SEV-SNP, and software-only SEV-SNP forgery before AMD's fixes. These are inherited hardware limits; a governance analysis explains why physical access matters in a treaty setting. Related finding: https://trustbutveri.fyi/mechanisms/tee-remote-attestation/evidence/flaws/1/.

  Response: Intel and AMD place the physical attack class outside their threat models, according to the researchers. AMD reports firmware 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.

**Family finding context**

- Context for SASH confidential network logger. Findings from the mechanism family appear here as context. They apply to an implementation only when its own record lists them, under the conditions stated there. Output nondeterminism leaves covert capacity (known failure, theoretical argument, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/evidence/flaws/1/) [16][17]. Hashing cannot remove information hidden in the outputs themselves. The Secure Gateway Device paper estimates that about 0.1 bit per token remains even with seed-synchronized replay checks. For a 200k-GPU inference cluster at full load (2,000 tokens per GPU per second), that is about 40 Mbit/s of covert egress, enough to move a 1 TB model in under three days. The paper names this the core remaining challenge and points to deterministic replay or active scrubbing of hardware-induced entropy. An independent study found that an adversary who chooses the prompts roughly doubles the bits leaked per token under Gumbel-based inference verification; see Bounding unexplained information in outputs.

  Related mechanism: Deterministic and bit-exact inference (R3, not in the proposal). Deterministic replay is one of the two remedies the flaw's source names.

  Related mechanism: Bounding unexplained information in outputs (R2, not in the proposal). Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict.
- Context for SASH confidential network logger. Findings from the mechanism family appear here as context. They apply to an implementation only when its own record lists them, under the conditions stated there. Some links cannot be passively tapped (scope limitation, open question, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/evidence/flaws/2/) [18][19]. Cankaya notes that copper-connected scale-up domains (for example NVL72 racks and TPU v7 cubes) are much harder to tap than fibre, and that optical budgets make passive taps impractical on 400GBASE-SR8 multimode links. Amodo found no taps advertised for 53 GBaud links as of May 2026.
- Context for SASH confidential network logger. Findings from the mechanism family appear here as context. They apply to an implementation only when its own record lists them, under the conditions stated there. Encrypted fabrics hide plaintext from both parties (scope limitation, open question, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/evidence/flaws/3/) [18]. Cankaya notes that with TEE-protected sessions whose keys are ephemeral and managed inside the TEE, neither the operator nor the manufacturer can recover session keys after the session, so tapped traffic could not be opened for recomputation. For other encrypted fabrics, the operator can retain keys.
- Context for SASH confidential network logger. Findings from the mechanism family appear here as context. They apply to an implementation only when its own record lists them, under the conditions stated there. Residual side channels in simple passive setups (known failure, theoretical argument, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/evidence/flaws/4/) [20]. Amodo's analysis of its own tapped prototype lists unvalidated header fields, timing of permitted traffic and variation in response formatting as residual channels, and concludes that the passive tap must be replaced by an active one.
- Context for SASH confidential network logger. Findings from the mechanism family appear here as context. They apply to an implementation only when its own record lists them, under the conditions stated there. Completeness rests on physical monitoring left out of scope (scope limitation, open question, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/evidence/flaws/5/) [16]. The Secure Gateway Device paper assumes the facility is physically monitored, and states that the whole architecture depends on the device being the only communication channel. It names radio emanation, power-line signalling and thermal channels as covert channels beyond that scope.

  Related mechanism: Side-channel suppression for isolated facilities (R1, not in the proposal). Addresses the radio, power-line and thermal channels that network-level designs leave out.
- Context for SASH confidential network logger. Findings from the mechanism family appear here as context. They apply to an implementation only when its own record lists them, under the conditions stated there. Verifier dictionary attacks on hashes (known failure, theoretical argument, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/evidence/flaws/6/) [16]. Hashes of very short outputs could be brute-forced by the verifier. The paper recommends hashing at least 5 tokens together, or at least 10 if the attacker filters for likely tokens.

**Scope limitations**

- Attestation shows a safeguard ran, not that it is effective (scope limitation, theoretical argument, in Safeguard attestation; https://trustbutveri.fyi/mechanisms/safeguard-attestation/evidence/flaws/1/) [1]. Proof of guardrail ensures that the guardrail executed, but the guardrail can still err or be jailbroken. Because the guardrail must be open source, a malicious developer can attack it with jailbreaks while still presenting a valid proof. In the authors' evaluation, Llama Guard 3 reached an F1 score of 0.56 on the unsafe class of the ToxicChat dataset. The authors state that proof of guardrail should not be interpreted or advertised as proof of safety.
- Selective attestation leaves traffic uncovered (scope limitation, theoretical argument, in Safeguard attestation; https://trustbutveri.fyi/mechanisms/safeguard-attestation/evidence/flaws/2/) [1][4][9]. Attestations are issued per response. In the prototype, the agent offers them when it receives high-stakes questions, so nothing shows that unattested traffic went through the same path. PAL*M's authors note that a prover could cherry-pick favourable executions, and suggest verifier-published nonces or requesting only session-level proofs. A governance analysis notes that auditors also need assurance that all activity is accounted for, since a host could start a second confidential virtual machine that bypasses monitoring.

  Related mechanism: On-chip telemetry from timing, memory and performance counters (R2, not in the proposal). On-chip counters are a proposed route to evidence about everything a chip runs, including a second virtual machine that skips the safeguard.
- Measurements may omit behaviour-relevant configuration or runtime changes (scope limitation, theoretical argument, in Safeguard attestation; https://trustbutveri.fyi/mechanisms/safeguard-attestation/evidence/flaws/3/) [9]. Every component that influences inference behaviour must be covered by the launch measurement, including feature flags, environment variables and invocation arguments. A launch measurement also does not show that a program keeps running as measured if the kernel is later compromised.
- Logger hardware supply chain (scope limitation, open question, in SASH confidential network logger; https://trustbutveri.fyi/implementations/sash-confidential-network-logger/evidence/flaws/3/) [14]. The prototype uses a Raspberry Pi 5 as the logger, which SASH says locks the design into Broadcom and Arm supply chains.

**Open questions**

- Recomputation cluster security is not monitored (open question, open question, in SASH confidential network logger; https://trustbutveri.fyi/implementations/sash-confidential-network-logger/evidence/flaws/1/) [14]. SASH states that the current prototype has no means to monitor the security of the recomputation cluster, which holds a copy of the model and decides whether an alarm is raised.
- Side channels not yet addressed (open question, open question, in SASH confidential network logger; https://trustbutveri.fyi/implementations/sash-confidential-network-logger/evidence/flaws/2/) [14]. SASH lists eliminating a wider range of side-channel vulnerabilities as future work.

**Not yet demonstrated**

- Network taps and certifiers: Proposed (legacy code R1), assessed for telling inference from training on a mutually inspected cluster


## Possible additions

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

- **Hardware-enabled guarantees (flexHEG) and guarantee processors** (Proposed (legacy code R1), assessed for checking and enforcing training-compute limits on chips, against adversaries up to states)
  - Bears on the open significant failure "Memory-bus interposition extracts attestation keys and forges attestations" in Safeguard 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** (Operational use (legacy code R3), assessed for reproducing open-model inference from receipts in Gensyn's information-market service)
  - Network taps and certifiers waits on it: Exact-match recomputation requires reproducible inference.
- **Hardware-attested weight binding** (Operational use (legacy code R3), assessed for hardware-attested weight binding showing users that a service runs its committed weights)
  - Safeguard attestation waits on it: Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation.
- **TEE remote attestation for AI workloads** (Operational use (legacy code R3), assessed for showing which software ran to a party that distrusts the operator holding the hardware)
  - Safeguard attestation waits on it: Frontier model inference typically needs several GPUs, GPU confidential computing is less mature than CPU support, and CPU inference, which an enclave prototype had to use, ran about 100 times slower than GPU inference.
  - Safeguard attestation waits on it: Trust rests on a small number of hardware vendors, and a per-CPU Intel attestation key has been extracted by physical attack.
- **Tamper evidence for verifier devices** (Research demonstration (legacy code R2), assessed for detecting probing of proposed verifier hardware, using server and electronics prototypes as evidence)
  - Network taps and certifiers depends on it.


## Dependencies

**Missing prerequisites**

- TEE remote attestation for AI workloads (Operational use (legacy code R3), assessed for showing which software ran to a party that distrusts the operator holding the hardware), needed by Safeguard attestation
- Hardware-attested weight binding (Operational use (legacy code R3), assessed for hardware-attested weight binding showing users that a service runs its committed weights), needed by Safeguard attestation
- Deterministic and bit-exact inference (Operational use (legacy code R3), assessed for reproducing open-model inference from receipts in Gensyn's information-market service), needed by Network taps and certifiers
- Tamper evidence for verifier devices (Research demonstration (legacy code R2), assessed for detecting probing of proposed verifier hardware, using server and electronics prototypes as evidence), needed by Network taps and certifiers

**Blockers**

- Safeguard attestation: No published design shows that all of a provider's traffic passes through the attested safeguard path; current evidence covers individual attested responses. (coverage & hidden compute) [1][9]
- Safeguard attestation: Frontier model inference typically needs several GPUs, GPU confidential computing is less mature than CPU support, and CPU inference, which an enclave prototype had to use, ran about 100 times slower than GPU inference. (performance & compatibility; waits on TEE remote attestation for AI workloads) [9][21]
- Safeguard attestation: Trust rests on a small number of hardware vendors, and a per-CPU Intel attestation key has been extracted by physical attack. (hardware trust; waits on TEE remote attestation for AI workloads) [7][9]
- Safeguard attestation: Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation. (evidence binding; waits on Hardware-attested weight binding) [21][22]
- Safeguard attestation: No independent red-team or audit of a safeguard-attestation system has been published, and the available prototypes are described by their authors as proofs of concept that have not been stress-tested by a counterparty. (adversarial validation) [2][6]
- Network taps and certifiers: The planned FPGA logger has not yet been built. (hardware trust) [14]
- Network taps and certifiers: The design has not been scaled to production traffic volumes. (performance & compatibility) [14]
- Network taps and certifiers: Exact-match recomputation requires reproducible inference. (evidence binding; waits on Deterministic and bit-exact inference) [15]


## What the verifier sees

- Model weights: shown by none; depends on the design for Safeguard attestation; hidden by none; not involved in none; unspecified for Network taps and certifiers.
- Inputs and outputs: shown by none; depends on the design for Safeguard attestation; hidden by none; not involved in none; unspecified for Network taps and certifiers.
- Training data: shown by none; depends on the design for none; hidden by none; not involved in Safeguard attestation; unspecified for Network taps and certifiers.

## Implementations

- Safeguard attestation: none on the map
- Network taps and certifiers: [AI 2040 inference-only verification stack](https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/) (R1, proposed architecture); [Low-trust AI compute verification system overview](https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/) (R1, proposed architecture); [SASH confidential network logger](https://trustbutveri.fyi/implementations/sash-confidential-network-logger/) (R1, research prototype)

## Sources

1. Proof-of-Guardrail in AI Agents and What (Not) to Trust from It, X. Jin et al. (2026). https://arxiv.org/abs/2603.05786
2. Verifiable-ClawGuard: proof-of-guardrail reference code, SaharaLabsAI (2026). https://github.com/SaharaLabsAI/Verifiable-ClawGuard
3. Safety Without Compromising on Privacy, D. McCann-Sayles et al. (2026). https://tinfoil.sh/blog/2026-09-14-safety-without-compromising-privacy
4. PAL*M: Property Attestation for Large Generative Models, P. Chantasantitam et al. (2026). https://arxiv.org/abs/2601.16199
5. Enabling Verifiably-Scoped Monitoring through Large Language Models and Trusted Compute, B. Penchas et al. (2026). https://icml.cc/virtual/2026/78630
6. Auditor-in-a-Box: Tools for Third-Party Auditing, R. Rinberg & B. Penchas (2026). https://www.lesswrong.com/posts/uWYk7MM9hAf9GEbGe/auditor-in-a-box-tools-for-third-party-auditing
7. TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition, J. Chuang et al. (2026). https://tee.fail/
8. DDRop: Active Memory Interposer Attacks on Confidential VMs by Dropping DDR5 Writes, J. De Meulemeester et al. (2026). https://ddropattack.eu/
9. 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
10. Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing, J. De Meulemeester et al. (2026). https://batteringram.eu/
11. RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP, B. Schlüter & S. Shinde (2025). https://rmpocalypse.github.io/
12. SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020), AMD (2025). https://www.amd.com/en/resources/product-security/bulletin/amd-sb-3020.html
13. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). https://intelligence.org/wp-content/uploads/2026/06/A-system-overview-for-near-term-low-trust-AI-compute-verification.pdf
14. Internationalising AI Verification, Singapore AI Safety Hub (SASH) (2026). https://www.aisafety.sg/research/internationalising-ai-verification
15. inference-verification: Inference Verification Prototype, Singapore AI Safety Hub (SASH) (2026). https://github.com/sg-ai-safety-hub/inference-verification
16. Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors, N. Cankaya et al. (2026). https://arxiv.org/abs/2606.10724
17. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). https://arxiv.org/abs/2608.23375
18. The Fundamentals and Feasibility of Secure Network Taps for Verifying AI Datacenter Use, N. Cankaya (2026). https://nacicankaya.substack.com/p/research-note-the-fundamentals-and
19. Network Tapping for AI Verification: A Technical Assessment, Amodo Design (2026). https://amododesign.com/notes/2026-05-03-network-tapping/
20. Fitting a Network TAP to our Inference Verification Prototype, Amodo Design (2026). https://amododesign.com/notes/2026-09-15-network-tap-inference-verification/
21. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). https://arxiv.org/abs/2506.23706
22. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). https://tinfoil.sh/blog/2026-02-03-proving-model-identity