# 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-0002,M-0001

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 | R2 | Adversarial | Analysis | Retrofit device | 0 / 3 / 0 | not involved | not involved | not involved |
| Deterministic and bit-exact inference | R3 | Adversarial | Analysis | None | 0 / 1 / 1 | depends | depends | not involved |
| Sampled inference recomputation | R3 | Adversarial | Analysis | None | 0 / 3 / 1 | depends | depends | not involved |

## Claims

No claims chosen.

## Mechanisms

### 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.

### Deterministic and bit-exact inference

Making model inference reproducible bit for bit, so that a verifier's re-run must match the provider's output exactly rather than approximately. ([Deterministic and bit-exact inference](https://trustbutveri.fyi/mechanisms/deterministic-inference/))

- Assessment: mechanism family.
- Readiness: R3 In production, assessed for reproducing open-model inference from receipts in Gensyn's information-market service.
- Claims in this proposal: none of them.
- Threat model: adversarial prover. Hardware: none. Prover cooperation: required. Attack testing: analysis. Category: Cryptographic & computational.
- What the verifier sees: model weights depends; inputs and outputs depends; training data not involved. Exact replay needs the weights, configuration and replayed requests inside the recomputation environment. What the verifier sees depends on whether that environment keeps them confidential.

### Sampled inference recomputation

A verifier re-runs a random sample of an AI provider's logged queries on a trusted copy of the declared model and checks the outputs match. ([Sampled inference recomputation](https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/))

- Assessment: mechanism family.
- Readiness: R3 In production, assessed for checking untrusted workers' activations against the declared model, prompt and precision.
- Claims in this proposal: none of them.
- Threat model: adversarial prover. Hardware: none. Prover cooperation: required. Attack testing: analysis. Category: Cryptographic & computational.
- What the verifier sees: model weights depends; inputs and outputs depends; training data not involved. Recomputation needs the weights and sampled requests inside the checking environment. For closed models, the record describes a trusted, confidential environment; disclosure to the verifier depends on that boundary.


## Properties

**In production**

- Deterministic and bit-exact inference: R3 In production, assessed for reproducing open-model inference from receipts in Gensyn's information-market service
- Sampled inference recomputation: R3 In production, assessed for checking untrusted workers' activations against the declared model, prompt and precision

**Built for an adversarial prover**

- Tamper evidence for verifier devices
- Deterministic and bit-exact inference
- Sampled inference recomputation

**No new hardware needed**

- Deterministic and bit-exact inference
- Sampled inference recomputation


## 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
- Deterministic and bit-exact inference: Analysis
- Sampled inference recomputation: Analysis


## Limits

**Open significant flaws**

- 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.
- Security depends on inspection protocols (theoretical argument, in Tamper evidence for verifier devices; https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/#flaw-2) [6][9]. 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) [1][2][10]. 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.
- Cross-hardware replay relies on reverse-engineered, closed behaviour (open question, in Deterministic and bit-exact inference; https://trustbutveri.fyi/mechanisms/deterministic-inference/#flaw-2) [11][13]. Emulating one GPU's rounding on another requires reverse-engineering tensor-core arithmetic and modelling proprietary kernel choices. Hawkeye covers a subset of NVIDIA architectures and states that attention and other higher-level operations need further reverse engineering. For the bit-exact emulator, a proprietary Hopper kernel family is an open edge case.
- Tolerance for numerical noise leaves a covert channel (demonstrated attack, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-1) [11][21][29]. Schemes that accept approximate matches can put an upper bound on an adversary's covert bandwidth, but they cannot close the channel. The weight-exfiltration detector cut exfiltratable information to under 0.5%, not to zero, on a 30-billion-parameter mixture-of-experts model under benign prompt traffic. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token. Across six models, that cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target the check that outputs match the declared model.

  Related mechanism: Deterministic and bit-exact inference (R3, in the proposal). Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration.
- Only recorded traffic is checked (theoretical argument, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-2) [21][32]. Recomputation checks that recorded, declared workloads are correct. It cannot show that the record is complete. The published schemes do not cover hidden workloads run on the same compute, or substituted work. Rinberg et al. say their exfiltration-detection scheme cannot stand alone.

  Related mechanism: Network taps and certifiers (R1, not in the proposal). Taps copy and hash all traffic on the monitored links, which bears on whether the traffic record is complete. They do not show what else ran on the same chips.
- Some inference optimizations are not covered (theoretical argument, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-3) [22][23]. TOPLOC's authors state that it cannot detect speculative decoding in which a cheaper model does the decoding. They did not test whether it distinguishes types of key-value (KV) cache compression. DiFR was evaluated only on sampling from a single model. Its authors sketch an extension to one speculative-decoding algorithm but do not test it.

**Open minor flaws**

- Some kernels remain genuinely nondeterministic (open question, in Deterministic and bit-exact inference; https://trustbutveri.fyi/mechanisms/deterministic-inference/#flaw-1) [11]. The bit-exact work separates kernels that are deterministic but not batch-invariant from truly nondeterministic ones that use atomic functions. Some integer de-quantization kernels use atomic additions and remain nondeterministic, so exact replay needs backends that avoid them.
- Mixed hardware widens the honest baseline (open question, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-4) [22]. When honest reference runs span different GPU types, the spread of benign scores grows. In DiFR's tests on Qwen3-30B-A3B, pooling A100 and H200 runs left Token-DiFR unable to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy separated them. Matched provider and verifier environments, or pooling that weights rare large deviations, restored detection.


## 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.

- **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 "Only recorded traffic is checked" in Sampled inference recomputation. Taps copy and hash all traffic on the monitored links, which bears on whether the traffic record is complete. They do not show what else ran on the same chips.
  - Sampled inference recomputation waits on it: In tap-based retrofit designs, recording all inference traffic needs network taps and recomputation servers that can ingest it, in the worst case one recomputation-server network interface per inference front-end interface.


## Dependencies

**Blockers**

- Tamper evidence for verifier devices: No tamper-evident enclosure has been designed for AI verifier hardware at retrofit scale. (hardware trust) [7]
- 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) [2]
- Tamper evidence for verifier devices: Active monitoring needs power, and visual inspection of large enclosures faces access limits. (access & governance) [6]
- Tamper evidence for verifier devices: No evaluation has been published in the AI verification setting. (adversarial validation) [7]
- Deterministic and bit-exact inference: Batch-invariant kernels cost throughput: in Thinking Machines' Qwen3-8B test, an improved deterministic build took 42 s against 26 s for vLLM's default, and SGLang reports an average 34.35% slowdown on its FlashInfer and FlashAttention 3 backends. (performance & compatibility) [12][14]
- Deterministic and bit-exact inference: Coverage is incomplete: the bit-exact emulator targets dense blocks on NVIDIA GPUs and excludes mixture-of-experts inference and training, and vLLM's batch-invariant mode is in beta, with open work on AMD hardware and speculative decoding. (performance & compatibility) [11][15][33]
- Deterministic and bit-exact inference: Amodo's status page for the AI 2040 verification plan rates a reproducible inference stack for that plan as 'not started'. (performance & compatibility) [28]
- Deterministic and bit-exact inference: Exact replay requires the prover to disclose weights, software versions, parallelism and batch sizes to whoever recomputes. (privacy & leakage) [7][11]
- Sampled inference recomputation: In tap-based retrofit designs, recording all inference traffic needs network taps and recomputation servers that can ingest it, in the worst case one recomputation-server network interface per inference front-end interface. (coverage & hidden compute; waits on Network taps and certifiers) [28][34]
- Sampled inference recomputation: In retrofit designs, the recomputation server must sit inside the prover's data centre, possibly under the prover's physical control, and still be protected from a compromised provider, which Amodo rates 'not on track'. (hardware trust) [21][28]
- Sampled inference recomputation: No independent red-team of a recomputation consistency check has been published (the one independent attack study targets the weight-exfiltration bound), and Amodo rates recomputation red-teaming 'not started'. (adversarial validation) [28][29]
- Sampled inference recomputation: Tolerance-based checks need calibration on trusted hardware and exact knowledge of the provider's sampling procedure, and in one prototype a sampling-implementation mismatch produced large spurious differences. (performance & compatibility) [22][27]
- Sampled inference recomputation: The verifier needs the model weights, so checking a closed-weights model requires a trusted, confidential recomputation environment, which the retrofit designs place inside the prover's facility. (privacy & leakage) [7][22][32]


## What the verifier sees

- Model weights: shown by none; depends on the design for Deterministic and bit-exact inference and Sampled inference recomputation; hidden by none; not involved in Tamper evidence for verifier devices; unspecified for none.
- Inputs and outputs: shown by none; depends on the design for Deterministic and bit-exact inference and Sampled inference recomputation; hidden by none; not involved in Tamper evidence for verifier devices; unspecified for none.
- Training data: shown by none; depends on the design for none; hidden by none; not involved in Tamper evidence for verifier devices, Deterministic and bit-exact inference and Sampled inference recomputation; unspecified for none.

## 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)
- Deterministic and bit-exact inference: [Batch-invariant inference kernels (Thinking Machines)](https://trustbutveri.fyi/implementations/batch-invariant-inference-kernels/) (R2, open-source project); [Verde and RepOps (Gensyn)](https://trustbutveri.fyi/implementations/gensyn-verde-repops/) (R3, product); [Low-trust AI compute verification system overview](https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/) (R1, proposed architecture)
- Sampled inference recomputation: [AI 2040 inference-only verification stack](https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/) (R1, proposed architecture); [DiFR (Divergence From Reference)](https://trustbutveri.fyi/implementations/difr/) (R2, research prototype); [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); [TOPLOC](https://trustbutveri.fyi/implementations/toploc/) (R3, open-source project)

## Sources

1. Anti-Tamper Radio: System-Level Tamper Detection for Computing Systems, P. Staat et al. (2022). https://ieeexplore.ieee.org/document/9833631/
2. Secure Physical Enclosures from Covers with Tamper-Resistance, V. Immler et al. (2019). https://tches.iacr.org/index.php/TCHES/article/view/7334
3. ImpedanceVerif: On-Chip Impedance Sensing for System-Level Tampering Detection, T. Mosavirik et al. (2023). https://eprint.iacr.org/2022/946
4. 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
5. PHYSEC SEAL: Change detection for maximum safety, PHYSEC GmbH (2026). https://www.physec.de/en/solutions/physec-seal/
6. Tamper-Indicating Enclosures, A Current Survey, H. A. Smartt & Z. N. Gastelum (2015). https://www.osti.gov/servlets/purl/1256541
7. 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
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. Anti-Tamper Radio Meets Reconfigurable Intelligent Surface for System-Level Tamper Detection, M. S. Tabar et al. (2025). https://arxiv.org/abs/2503.14279
11. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). https://arxiv.org/abs/2606.00279
12. Defeating Nondeterminism in LLM Inference, H. He & Thinking Machines Lab (2025). https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/
13. Hawkeye: Reproducing GPU-Level Non-Determinism, E. Badash et al. (2026). https://proceedings.mlsys.org/paper_files/paper/2026/hash/e217c271a57c365a246b0ad39e668ba8-Abstract-Conference.html
14. Towards Deterministic Inference in SGLang and Reproducible RL Training, The SGLang Team (2025). https://www.lmsys.org/blog/2025-09-22-sglang-deterministic/
15. Batch Invariance (vLLM documentation), vLLM project (2026). https://github.com/vllm-project/vllm/blob/main/docs/features/batch_invariance.md
16. gensyn-ai/ree: Gensyn Reproducible Execution Environment (GitHub repository), Gensyn (2026). https://github.com/gensyn-ai/ree
17. EigenCloud Brings Verifiable AI to Mass Market with EigenAI and EigenCompute Launches, EigenCloud (2025). https://www.eigenlabs.org/blog/eigencloud-brings-verifiable-ai-to-mass-market-with-eigenai-and-eigencompute-launches/
18. Building Delphi: Pricing, Settlement, and Agentic Trading, D. Jedamski (2026). https://www.gensyn.ai/blog/building-delphi-pricing-settlement-and-agentic-trading
19. Reproducible Execution Environment (REE) (Gensyn documentation), Gensyn (2026). https://docs.gensyn.ai/tech
20. What is Delphi? (Delphi documentation), Gensyn (2026). https://docs.delphi.fyi/
21. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). https://arxiv.org/abs/2511.02620
22. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). https://arxiv.org/abs/2511.20621
23. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). https://proceedings.mlr.press/v267/ong25a.html
24. PrimeIntellect-ai/toploc (GitHub repository), Prime Intellect (2025). https://github.com/PrimeIntellect-ai/toploc
25. INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning, Prime Intellect Team et al. (2025). https://arxiv.org/abs/2505.07291
26. adamkarvonen/difr (GitHub repository), A. Karvonen (2025). https://github.com/adamkarvonen/difr
27. Scaling Recomputation Inference Verification, Amodo Design (2026). https://amododesign.com/notes/2026-09-02-scaling-recomputation-inference-verification/
28. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). https://amododesign.com/ai-verification/plan-a-sitrep/
29. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). https://arxiv.org/abs/2608.23375
30. SYNTHETIC-2 Release: Four Million Collaboratively Generated Reasoning Traces, Prime Intellect (2025). https://www.primeintellect.ai/blog/synthetic-2-release
31. An Inference Verification Prototype — Stage 1, Amodo Design (2026). https://amododesign.com/notes/2026-06-29-inference-verification-prototype/
32. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). https://amododesign.com/notes/2026-06-23-verification-algorithms/
33. [Feature]: Batch Invariant Feature and Performance Optimization (vLLM issue #27433), vLLM project contributors (2025). https://github.com/vllm-project/vllm/issues/27433
34. Verification Plan, R. Dean (2026). https://ai-2040.com/supplements/verification-plan