# 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-0013,M-0017&implementations=M-0013:I-0011

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 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Network taps and certifiers / AI 2040 inference-only verification stack | R1 | Adversarial | None | Retrofit device | 0 / 3 / 0 | unspecified | unspecified | unspecified |
| Tamper evidence for verifier devices | R2 | Adversarial | Analysis | Retrofit device | 0 / 3 / 0 | not involved | not involved | not involved |

## Claims

No claims chosen.

## Mechanisms

### Network taps and certifiers

A proposed retrofit that isolates data-centre inference units, taps their front-end traffic and recomputes random samples to check that only declared inference runs. ([Network taps and certifiers](https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/))

- Assessment: selected implementation [AI 2040 inference-only verification stack](https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/).
- Readiness: R1 Proposed, assessed for showing that retrofitted data centres run only inference.
- Claims in this proposal: none of them.
- Threat model: adversarial prover. Hardware: retrofit device. Prover cooperation: required. Attack testing: none. 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.

### Tamper evidence for verifier devices

Enclosures, seals and sensors that make physical interference with verification hardware either visible or self-defeating. ([Tamper evidence for verifier devices](https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/))

- Assessment: mechanism family.
- Readiness: R2 Demonstrated, assessed for detecting probing of proposed verifier hardware, using server and electronics prototypes as evidence.
- Claims in this proposal: none of them.
- Threat model: adversarial prover. Hardware: retrofit device. Prover cooperation: partial. Attack testing: analysis. Category: Off-chip devices & sensors.
- What the verifier sees: model weights not involved; inputs and outputs not involved; training data not involved. Protects verifier devices; it does not handle model data.


## Properties

**Built for an adversarial prover**

- Network taps and certifiers
- Tamper evidence for verifier devices


## 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**

- Tamper evidence for verifier devices: Analysis


## Limits

**Open significant flaws**

- The recomputation server must be trusted (theoretical argument, in AI 2040 inference-only verification stack; https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/#flaw-1) [1][2][4]. The plan calls the integrity of the recomputation server an extremely important aspect, and its argument that sampling verifies all outputs assumes that the server's computations and outputs can be trusted. The companion page notes that the server sits inside the prover's facility, possibly under the prover's physical control, and that hardening it against integrity attacks needs significant research. Amodo rates recomputation-server security as not on track.
- Spare compute is not verified (theoretical argument, in AI 2040 inference-only verification stack; https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/#flaw-2) [1]. The plan states that it does not verify that spare compute is unused for unapproved workloads, because this seems very challenging. It relies instead on side-channel bounds and memory wipes, so that the only results that persist are verified inference outputs.
- A recomputation family degrades against prompt-controlling adversaries (demonstrated attack, in AI 2040 inference-only verification stack; https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/#flaw-3) [1][2][6][7]. The plan's companion page names DiFR among the recomputation schemes being tested. An independent study found that Gumbel-based inference verification, the family that includes Token-DiFR, leaks roughly twice as many bits per token when the adversary chooses prompts that disrupt the text's structure, across six models of 1 to 32 billion parameters. The slowdown it imposes on a hidden-signalling adversary falls from 146–254 times under benign prompts to 60–118 times. The attack weakens the bound on hidden information in outputs, which the plan relies on to keep undeclared results from leaving.
- Seals are often defeated with simple methods (demonstrated attack, in Tamper evidence for verifier devices; https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/#flaw-1) [18][19]. Mechanism-class evidence. Published defeats of general security seals. They warn about proposed verifier-device seals, but do not demonstrate defeat of an AI verification enclosure or sensor. In 1996 a Los Alamos vulnerability assessment defeated all 94 security seals it examined, with 132 defeats in total, using rapid, inexpensive, low-tech methods. It found that seal cost did not predict security. In 2001 Johnston reported that high-tech seals are often easier to defeat than low-tech ones.
- Security depends on inspection protocols (theoretical argument, in Tamper evidence for verifier devices; https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/#flaw-2) [16][19]. Mechanism-class evidence. An inspection and protocol requirement drawn from safeguards and enclosure studies, not a reported break of a deployed AI verifier. Johnston argues that a seal is no better than the protocols for using it, and that inspectors are usually given little useful information on how to detect tampering. The Sandia survey notes that larger enclosures are hard to inspect fully and that sensor data must be authenticated.
- Attack classes outside published models (open question, in Tamper evidence for verifier devices; https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/#flaw-3) [11][12][20]. Mechanism-class evidence. The radio compensation result is emulated using measured channel data under a known-reference attacker model. It is not a physical bypass demonstration against an AI verifier enclosure. The authors of the batteryless cover say they cannot assess chemical-solvent attacks, which exceed their expertise, and deem cover removal impractical. Anti-Tamper Radio's reference can drift as the environment or measurement system ages; the authors suggest gradually renewing the reference. A 2025 follow-up by some of the same authors shows, by emulation on measured channel data, that an attacker who knows the reference channel and the needle's effect on it could inject a signal that cancels the change caused by a needle insertion. It proposes a reconfigurable intelligent surface that randomizes the channel as a countermeasure.

**Family finding context**

- Context for AI 2040 inference-only verification stack; applicability depends on the finding's scope. Output nondeterminism leaves covert capacity (theoretical argument, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/#flaw-1) [7][8]. 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 AI 2040 inference-only verification stack; applicability depends on the finding's scope. Some links cannot be passively tapped (open question, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/#flaw-2) [9][10]. 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 AI 2040 inference-only verification stack; applicability depends on the finding's scope. Encrypted fabrics hide plaintext from both parties (open question, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/#flaw-3) [9]. 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 AI 2040 inference-only verification stack; applicability depends on the finding's scope. Residual side channels in simple passive setups (theoretical argument, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/#flaw-4) [5]. 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 AI 2040 inference-only verification stack; applicability depends on the finding's scope. Completeness rests on physical monitoring left out of scope (open question, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/#flaw-5) [8]. 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 AI 2040 inference-only verification stack; applicability depends on the finding's scope. Verifier dictionary attacks on hashes (theoretical argument, in Network taps and certifiers; https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/#flaw-6) [8]. 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.

**Not yet demonstrated**

- Network taps and certifiers: R1 Proposed, assessed for showing that retrofitted data centres run only inference


## 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.

- **Memory wiping and proofs of secure erasure** (R1 Proposed, assessed for showing that no data from earlier work persists in memory the wipe reaches)
  - Network taps and certifiers waits on it: Memory wiping may use existing algorithms, but hardware testing is at an early stage.
- **Side-channel suppression for isolated facilities** (R1 Proposed, assessed for bounding physical covert channels out of a verified enclosure)
  - Network taps and certifiers waits on it: There is no plan yet for quickly scaling side-channel defences on a frontier cluster; only early theoretical pieces exist.
- **Whole-workload recomputation (reproducible packets)** (R1 Proposed, assessed for recomputing whole workloads to show a cluster runs only declared inference)
  - Network taps and certifiers waits on it: A fully reproducible inference stack needs substantial software and tooling, and per-packet network reproducibility may need considerable software, firmware and possibly hardware work.
- **Sampled inference recomputation** (R3 In production, assessed for checking untrusted workers' activations against the declared model, prompt and precision)
  - Network taps and certifiers depends on it.


## Dependencies

**Missing prerequisites**

- Sampled inference recomputation (R3 In production, assessed for checking untrusted workers' activations against the declared model, prompt and precision), needed by Network taps and certifiers
- Whole-workload recomputation (reproducible packets) (R1 Proposed, assessed for recomputing whole workloads to show a cluster runs only declared inference), needed by Network taps and certifiers

**Blockers**

- Network taps and certifiers: A fully reproducible inference stack needs substantial software and tooling, and per-packet network reproducibility may need considerable software, firmware and possibly hardware work. (performance & compatibility; waits on Whole-workload recomputation (reproducible packets)) [2]
- Network taps and certifiers: Passive optical taps work at 400G, but the 800G and 1600G line rates now arriving in data centres are undemonstrated. (performance & compatibility; waits on Network taps and certifiers) [2]
- Network taps and certifiers: Checking that taps are correctly installed and stay in place at scale is not a solved problem, and hardening the recomputation server inside the prover's facility needs significant research. (hardware trust; waits on Tamper evidence for verifier devices) [2][4]
- Network taps and certifiers: There is no plan yet for quickly scaling side-channel defences on a frontier cluster; only early theoretical pieces exist. (coverage & hidden compute; waits on Side-channel suppression for isolated facilities) [2]
- Network taps and certifiers: Memory wiping may use existing algorithms, but hardware testing is at an early stage. (coverage & hidden compute; waits on Memory wiping and proofs of secure erasure) [2]
- Network taps and certifiers: Robust red-teaming of recomputation schemes has not started, and most algorithm development remains academic. (adversarial validation) [2][4]
- Tamper evidence for verifier devices: No tamper-evident enclosure has been designed for AI verifier hardware at retrofit scale. (hardware trust) [17]
- Tamper evidence for verifier devices: Battery-backed designs add bulk, limit operating temperature (+10 °C to +35 °C for the IBM 4765) and complicate transport. (performance & compatibility) [12]
- Tamper evidence for verifier devices: Active monitoring needs power, and visual inspection of large enclosures faces access limits. (access & governance) [16]
- Tamper evidence for verifier devices: No evaluation has been published in the AI verification setting. (adversarial validation) [17]


## What the verifier sees

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

## Implementations

- 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)
- Tamper evidence for verifier devices: [AI 2040 inference-only verification stack](https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/) (R1, proposed architecture)

## Sources

1. Verification Plan, R. Dean (2026). https://ai-2040.com/supplements/verification-plan
2. Get Involved in Verification, AI Futures Project (2026). https://ai-2040.com/supplements/verification-plan/get-involved
3. Verifying international AI deals: Plan A, the state-of-play, and what you can do to help, T. Milton et al. (2026). https://amodo.substack.com/p/verifying-international-ai-deals
4. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). https://amododesign.com/ai-verification/plan-a-sitrep/
5. Fitting a Network TAP to our Inference Verification Prototype, Amodo Design (2026). https://amododesign.com/notes/2026-09-15-network-tap-inference-verification/
6. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). https://arxiv.org/abs/2511.02620
7. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). https://arxiv.org/abs/2608.23375
8. Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors, N. Cankaya et al. (2026). https://arxiv.org/abs/2606.10724
9. 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
10. Network Tapping for AI Verification: A Technical Assessment, Amodo Design (2026). https://amododesign.com/notes/2026-05-03-network-tapping/
11. Anti-Tamper Radio: System-Level Tamper Detection for Computing Systems, P. Staat et al. (2022). https://ieeexplore.ieee.org/document/9833631/
12. Secure Physical Enclosures from Covers with Tamper-Resistance, V. Immler et al. (2019). https://tches.iacr.org/index.php/TCHES/article/view/7334
13. ImpedanceVerif: On-Chip Impedance Sensing for System-Level Tampering Detection, T. Mosavirik et al. (2023). https://eprint.iacr.org/2022/946
14. IBM 4765 Cryptographic Coprocessor Security Module: Security Policy, IBM Corporation (2012). https://csrc.nist.gov/csrc/media/projects/cryptographic-module-validation-program/documents/security-policies/140sp1505.pdf
15. PHYSEC SEAL: Change detection for maximum safety, PHYSEC GmbH (2026). https://www.physec.de/en/solutions/physec-seal/
16. Tamper-Indicating Enclosures, A Current Survey, H. A. Smartt & Z. N. Gastelum (2015). https://www.osti.gov/servlets/purl/1256541
17. 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
18. Physical Security and Tamper-Indicating Devices, R. G. Johnston & A. R. E. Garcia (1996). https://www.osti.gov/servlets/purl/459707
19. Tamper Detection for Safeguards and Treaty Monitoring: Fantasies, Realities, and Potentials, R. G. Johnston (2001). https://www.nonproliferation.org/wp-content/uploads/npr/81john.pdf
20. Anti-Tamper Radio Meets Reconfigurable Intelligent Surface for System-Level Tamper Detection, M. S. Tabar et al. (2025). https://arxiv.org/abs/2503.14279