# 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-0017,M-0014&implementations=M-0017: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 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Tamper evidence for verifier devices / AI 2040 inference-only verification stack | R1 | Adversarial | None | Retrofit device | 0 / 3 / 0 | unspecified | unspecified | unspecified |
| Bandwidth limits and compartmentalization | R2 | Adversarial | Analysis | Retrofit device | 0 / 5 / 0 | not involved | not involved | not involved |

## Claims

No claims chosen.

## Mechanisms

### Tamper evidence for verifier devices

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. ([Tamper evidence for verifier devices](https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/))

- 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.

### Bandwidth limits and compartmentalization

Capping or removing network links between groups of accelerators, so that serving within each group still works but large training across groups becomes far slower. ([Bandwidth limits and compartmentalization](https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/))

- Assessment: mechanism family.
- Readiness: R2 Demonstrated, assessed for monitoring inter-node traffic with operator-run software on four GPUs.
- Claims in this proposal: none of them.
- Threat model: adversarial prover. Hardware: retrofit device. Prover cooperation: required. Attack testing: analysis. Category: Isolation & system architectures.
- What the verifier sees: model weights not involved; inputs and outputs not involved; training data not involved. Caps traffic between groups of chips; it does not read the traffic's content.


## Properties

**Built for an adversarial prover**

- Tamper evidence for verifier devices
- Bandwidth limits and compartmentalization


## 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: 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.
- 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) [14][18][19]. 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.
- 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) [14]. 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.
- Undeclared local storage raises per-pod capacity (theoretical argument, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-3) [14]. More memory or storage per pod helps an adversary. Lucid requires per-pod storage to be declared, capped and physically inspected.
- Training within one pod is not covered (open question, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-4) [14]. 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.
- 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) [17]. 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.

**Family finding context**

- Context for AI 2040 inference-only verification stack; applicability depends on the finding's scope. 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) [8][9]. 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.
- Context for AI 2040 inference-only verification stack; applicability depends on the finding's scope. Security depends on inspection protocols (theoretical argument, in Tamper evidence for verifier devices; https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/#flaw-2) [9][10]. 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.
- Context for AI 2040 inference-only verification stack; applicability depends on the finding's scope. 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][13]. 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.

**Not yet demonstrated**

- Tamper evidence for verifier devices: 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)
  - Tamper evidence for verifier devices 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)
  - Tamper evidence for verifier devices waits on it: Passive optical taps work at 400G, but the 800G and 1600G line rates now arriving in data centres are undemonstrated.
  - Bandwidth limits and compartmentalization waits on it: The verifier must know that all traffic leaving a pod crosses the capped, monitored links.
- **Side-channel suppression for isolated facilities** (R1 Proposed, assessed for bounding physical covert channels out of a verified enclosure)
  - Tamper evidence for verifier devices 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)
  - Tamper evidence for verifier devices 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)
  - Tamper evidence for verifier devices 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 Tamper evidence for verifier devices
- Whole-workload recomputation (reproducible packets) (R1 Proposed, assessed for recomputing whole workloads to show a cluster runs only declared inference), needed by Tamper evidence for verifier devices

**Shared foundations**

- Network taps and certifiers, relied on by Tamper evidence for verifier devices and Bandwidth limits and compartmentalization

**Blockers**

- Tamper evidence for verifier devices: 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]
- Tamper evidence for verifier devices: 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]
- Tamper evidence for verifier devices: 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]
- Tamper evidence for verifier devices: 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]
- Tamper evidence for verifier devices: 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]
- Tamper evidence for verifier devices: Robust red-teaming of recomputation schemes has not started, and most algorithm development remains academic. (adversarial validation) [2][4]
- Bandwidth limits and compartmentalization: No cap that a verifier can check has been implemented or red-teamed. (adversarial validation) [14]
- Bandwidth limits and compartmentalization: The verifier must know that all traffic leaving a pod crosses the capped, monitored links. (coverage & hidden compute; waits on Network taps and certifiers) [15]
- Bandwidth limits and compartmentalization: Shaping devices and routing assignments must be trusted by both parties; Amodo has not yet fully analysed resilience to a compromised DPU. (hardware trust; waits on Tamper evidence for verifier devices) [14][17]
- Bandwidth limits and compartmentalization: Advances in low-communication training could shrink the margin that the cap enforces. (capacity bounds) [14][18][19]


## What the verifier sees

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

## Implementations

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

## 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. Physical Security and Tamper-Indicating Devices, R. G. Johnston & A. R. E. Garcia (1996). https://www.osti.gov/servlets/purl/459707
9. 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
10. Tamper-Indicating Enclosures, A Current Survey, H. A. Smartt & Z. N. Gastelum (2015). https://www.osti.gov/servlets/purl/1256541
11. Secure Physical Enclosures from Covers with Tamper-Resistance, V. Immler et al. (2019). https://tches.iacr.org/index.php/TCHES/article/view/7334
12. Anti-Tamper Radio: System-Level Tamper Detection for Computing Systems, P. Staat et al. (2022). https://ieeexplore.ieee.org/document/9833631/
13. Anti-Tamper Radio Meets Reconfigurable Intelligent Surface for System-Level Tamper Detection, M. S. Tabar et al. (2025). https://arxiv.org/abs/2503.14279
14. Traffic Shaping for Workload Classification, Lucid Computing (2026). https://lucidcomputing.substack.com/p/traffic-shaping-for-workload-classification
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. De-risking Interconnect Limits for AI Verification, A. Scher et al. (2026). https://techgov.intelligence.org/blog/de-risking-interconnect-limits-for-ai-verification
17. The Tray as a Bandwidth Boundary, Amodo Design (2026). https://amododesign.com/notes/2026-03-16-dpu-bandwidth-limiter/
18. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). https://arxiv.org/abs/2311.08105
19. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). https://arxiv.org/abs/2605.29359