# 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-0022,M-0017&implementations=M-0022: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 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Side-channel suppression for isolated facilities / 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

### Side-channel suppression for isolated facilities

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. ([Side-channel suppression for isolated facilities](https://trustbutveri.fyi/mechanisms/side-channel-suppression/))

- 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**

- Side-channel suppression for isolated facilities
- 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) [16][17]. 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) [14][17]. 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) [9][10][18]. 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. Supply-chain implants may evade inspection (theoretical argument, in Side-channel suppression for isolated facilities; https://trustbutveri.fyi/mechanisms/side-channel-suppression/#flaw-1) [8]. Cankaya identifies malicious hardware embedded deep in purchased components as a residual risk that visual inspection and disassembly may not catch. He notes that radiographic examination under high-security standards could mitigate it.
- Context for AI 2040 inference-only verification stack; applicability depends on the finding's scope. Openings for airflow, power and optics weaken shielding (theoretical argument, in Side-channel suppression for isolated facilities; https://trustbutveri.fyi/mechanisms/side-channel-suppression/#flaw-2) [8]. Cankaya notes that keeping attenuation high while passing high-power airflow, cabling and optical links adds complexity beyond existing shielded-enclosure specifications.
- Context for AI 2040 inference-only verification stack; applicability depends on the finding's scope. Inspection assumptions may not hold (open question, in Side-channel suppression for isolated facilities; https://trustbutveri.fyi/mechanisms/side-channel-suppression/#flaw-3) [8]. The design's statistical argument assumes that visual or disassembly inspection catches every flaw that is present in a sampled unit. Cankaya is unsure whether destructive teardowns are defence-dominant or offence-dominant.

**Not yet demonstrated**

- Side-channel suppression for isolated facilities: 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)
  - Side-channel suppression for isolated facilities waits on it: Memory wiping may use existing algorithms, but hardware testing is at an early stage.
- **Network taps and certifiers** (R1 Proposed, assessed for committing a complete record of cluster traffic, so declared inference can be checked)
  - Side-channel suppression for isolated facilities waits on it: Passive optical taps work at 400G, but the 800G and 1600G line rates now arriving in data centres are undemonstrated.
- **Whole-workload recomputation (reproducible packets)** (R1 Proposed, assessed for recomputing whole workloads to show a cluster runs only declared inference)
  - Side-channel suppression for isolated facilities 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)
  - Side-channel suppression for isolated facilities 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 Side-channel suppression for isolated facilities
- Whole-workload recomputation (reproducible packets) (R1 Proposed, assessed for recomputing whole workloads to show a cluster runs only declared inference), needed by Side-channel suppression for isolated facilities

**Blockers**

- Side-channel suppression for isolated facilities: 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]
- Side-channel suppression for isolated facilities: 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]
- Side-channel suppression for isolated facilities: 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]
- Side-channel suppression for isolated facilities: 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]
- Side-channel suppression for isolated facilities: 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]
- Side-channel suppression for isolated facilities: 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) [15]
- 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) [10]
- Tamper evidence for verifier devices: Active monitoring needs power, and visual inspection of large enclosures faces access limits. (access & governance) [14]
- Tamper evidence for verifier devices: No evaluation has been published in the AI verification setting. (adversarial validation) [15]


## 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 Side-channel suppression for isolated facilities.
- 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 Side-channel suppression for isolated facilities.
- Training data: shown by none; depends on the design for none; hidden by none; not involved in Tamper evidence for verifier devices; unspecified for Side-channel suppression for isolated facilities.

## Implementations

- Side-channel suppression for isolated facilities: [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); [RAND secure inference data center (SIDC) design](https://trustbutveri.fyi/implementations/rand-secure-inference-data-centers/) (R1, proposed architecture)
- 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. Suppressing Side Channels in an Untrusted Data Center via Retrofitted Defenses, N. Cankaya (2026). https://techgov.intelligence.org/blog/suppressing-side-channels-in-an-untrusted-data-center-via-retrofitted-defenses
9. Anti-Tamper Radio: System-Level Tamper Detection for Computing Systems, P. Staat et al. (2022). https://ieeexplore.ieee.org/document/9833631/
10. Secure Physical Enclosures from Covers with Tamper-Resistance, V. Immler et al. (2019). https://tches.iacr.org/index.php/TCHES/article/view/7334
11. ImpedanceVerif: On-Chip Impedance Sensing for System-Level Tampering Detection, T. Mosavirik et al. (2023). https://eprint.iacr.org/2022/946
12. 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
13. PHYSEC SEAL: Change detection for maximum safety, PHYSEC GmbH (2026). https://www.physec.de/en/solutions/physec-seal/
14. Tamper-Indicating Enclosures, A Current Survey, H. A. Smartt & Z. N. Gastelum (2015). https://www.osti.gov/servlets/purl/1256541
15. 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
16. Physical Security and Tamper-Indicating Devices, R. G. Johnston & A. R. E. Garcia (1996). https://www.osti.gov/servlets/purl/459707
17. 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
18. Anti-Tamper Radio Meets Reconfigurable Intelligent Surface for System-Level Tamper Detection, M. S. Tabar et al. (2025). https://arxiv.org/abs/2503.14279