# 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-0002,M-0012&implementations=M-0012:I-0007

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 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Deterministic and bit-exact inference | Operational use | Published security analysis | Adversarial | Analysis | None | 0 / 0 / 0 | depends | depends | not involved |
| Hardware-attested weight binding / Attestable Audits | Research demonstration | Published security analysis | Semi-trusted | Analysis | Existing features | 0 / 0 / 0 | unspecified | unspecified | unspecified |

## Claims

No claims chosen.

## Mechanisms

### 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.
- Development: Operational use (legacy code R3), assessed for reproducing open-model inference from receipts in Gensyn's information-market service.
- Security evidence: Published security analysis. Independent evaluation: unassessed. Formal proof: unassessed. Deployment assurance: unassessed.
- 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.

### Hardware-attested weight binding

A research prototype that runs AI safety benchmarks inside a trusted execution environment and publishes hardware-signed records linking the model, the audit and the results. ([Hardware-attested weight binding](https://trustbutveri.fyi/mechanisms/model-identity-attestation/))

- Assessment: selected implementation [Attestable Audits](https://trustbutveri.fyi/implementations/attestable-audits/).
- Development: Research demonstration (legacy code R2), assessed for showing users that the model answering them is the audited one.
- 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: On-chip & hardware-enabled.
- 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

**Operational use**

- Deterministic and bit-exact inference: Operational use (legacy code R3), assessed for reproducing open-model inference from receipts in Gensyn's information-market service

**Built for an adversarial prover**

- Deterministic and bit-exact inference

**No new hardware needed**

- Deterministic and bit-exact inference
- Hardware-attested weight binding


## 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**

- Deterministic and bit-exact inference: Analysis
- Hardware-attested weight binding / Attestable Audits: Analysis


## Limits

**Family finding context**

- Context for Attestable Audits. 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. Underlying attestation can be forged or relayed (known failure, demonstrated attack, in Hardware-attested weight binding; https://trustbutveri.fyi/mechanisms/model-identity-attestation/evidence/flaws/1/) [14][15][16][17][18][19]. Inherited finding. Critical for weight binding against an operator with physical access to affected hardware, or with control of the hypervisor on an AMD SEV-SNP platform without AMD's fixes. PAL*M excludes physical attacks, and Tinfoil acknowledges this boundary. The enclave route inherits the platform-specific TEE attestation failures. Intel TDX forgery and H100 relay were demonstrated with physical access and host control. Battering RAM defeated AMD SEV-SNP attestation on DDR4 servers; RMPocalypse did so from malicious host software on platforms without AMD's fixes. These demonstrate failures of the trust roots, not of each model-commitment protocol. Related finding: https://trustbutveri.fyi/mechanisms/tee-remote-attestation/evidence/flaws/1/.

  Response: The TEE.fail authors report that physical interposer attacks are outside Intel's and AMD's threat models. AMD reports 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.
- Context for Attestable Audits. 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. Launch-state attestation does not by itself cover weights loaded later (known failure, theoretical argument, in Hardware-attested weight binding; https://trustbutveri.fyi/mechanisms/model-identity-attestation/evidence/flaws/2/) [20][21]. Attestation measures launch state, and weights are read from disk after boot. A signature checked at load time does not stop a malicious hypervisor from altering the disk afterwards. Tinfoil reports mitigating this with dm-verity checks on every read. Unmeasured runtime configuration remains a general risk.
- Context for Attestable Audits. 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. For private models, a user can confirm consistency but not content (scope limitation, open question, in Hardware-attested weight binding; https://trustbutveri.fyi/mechanisms/model-identity-attestation/evidence/flaws/3/) [12][20]. When weights are not published, users can check that the same root hash is served each time, but not what the model is. Pairing the hash with an attested evaluation, as in Attestable Audits, is one proposed remedy.

**Scope limitations**

- Some kernels remain genuinely nondeterministic (scope limitation, open question, in Deterministic and bit-exact inference; https://trustbutveri.fyi/mechanisms/deterministic-inference/evidence/flaws/1/) [1]. 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.
- Cross-hardware replay relies on reverse-engineered, closed behaviour (scope limitation, open question, in Deterministic and bit-exact inference; https://trustbutveri.fyi/mechanisms/deterministic-inference/evidence/flaws/2/) [1][3]. 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.
- Relies on the TEE vendor and inherits TEE attacks (scope limitation, theoretical argument, in Attestable Audits; https://trustbutveri.fyi/implementations/attestable-audits/evidence/flaws/1/) [12]. Inherited finding. The prototype trusts AWS Nitro, not the Intel TDX or AMD SEV-SNP attestation roots targeted by the cited confidential-VM studies. Those studies are class context, not a demonstrated attack on this Nitro prototype. The design depends on trusting the TEE vendor, AWS in the prototype. The authors cite memory-aliasing, ciphertext side-channel and malicious-interrupt attacks on confidential VMs (BadRAM, CIPHERLEAKS, Heckler). Their answer is to revoke vulnerable base images once such attacks are discovered. Related finding: https://trustbutveri.fyi/mechanisms/tee-remote-attestation/evidence/flaws/5/.

  Response: The authors propose revoking vulnerable base images; they do not report a red-team evaluation of the prototype.
- CPU-only enclaves force small, quantized models and high cost (scope limitation, open question, in Attestable Audits; https://trustbutveri.fyi/implementations/attestable-audits/evidence/flaws/3/) [12][13]. Memory limits required 4-bit quantization, and the quantized model scored 51.4% on zero-shot MMLU. CPU inference cost 21.7 times as much per token as GPU inference, and the enclave roughly doubled the CPU cost. The authors wrote that H100 confidential computing had no multi-GPU support. NVIDIA's white paper of August 2025 describes a protected-PCIe mode that passes all eight GPUs of a Hopper HGX node to one confidential VM, with NVLink traffic unencrypted.

**Open questions**

- Prompt-based model exfiltration is a residual gap (open question, open question, in Attestable Audits; https://trustbutveri.fyi/implementations/attestable-audits/evidence/flaws/2/) [12]. The authors state that "prompt-based model exfiltration during the user interaction step remains a residual gap".


## 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.

- **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)
  - Hardware-attested weight binding waits on it: The prototype needs porting to GPU confidential computing to handle larger models; the authors expect an overhead as small as 5 times there.


## 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 Hardware-attested weight binding

**Blockers**

- 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) [2][4]
- 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) [1][5][22]
- 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) [23]
- Deterministic and bit-exact inference: Exact replay requires the prover to disclose weights, software versions, parallelism and batch sizes to whoever recomputes. (privacy & leakage) [1][11]
- Hardware-attested weight binding: The prototype needs porting to GPU confidential computing to handle larger models; the authors expect an overhead as small as 5 times there. (performance & compatibility; waits on TEE remote attestation for AI workloads) [12]
- Hardware-attested weight binding: As of September 2026 no code has been released for the prototype. (adversarial validation) [12]


## What the verifier sees

- Model weights: shown by none; depends on the design for Deterministic and bit-exact inference; hidden by none; not involved in none; unspecified for Hardware-attested weight binding.
- Inputs and outputs: shown by none; depends on the design for Deterministic and bit-exact inference; hidden by none; not involved in none; unspecified for Hardware-attested weight binding.
- Training data: shown by none; depends on the design for none; hidden by none; not involved in Deterministic and bit-exact inference; unspecified for Hardware-attested weight binding.

## Implementations

- 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)
- Hardware-attested weight binding: [Attestable Audits](https://trustbutveri.fyi/implementations/attestable-audits/) (R2, research prototype); [PAL*M](https://trustbutveri.fyi/implementations/palm/) (R2, research prototype); [Tinfoil model identity (Modelwrap)](https://trustbutveri.fyi/implementations/tinfoil-model-identity/) (R3, product)

## Sources

1. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). https://arxiv.org/abs/2606.00279
2. Defeating Nondeterminism in LLM Inference, H. He & Thinking Machines Lab (2025). https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/
3. Hawkeye: Reproducing GPU-Level Non-Determinism, E. Badash et al. (2026). https://proceedings.mlsys.org/paper_files/paper/2026/hash/e217c271a57c365a246b0ad39e668ba8-Abstract-Conference.html
4. Towards Deterministic Inference in SGLang and Reproducible RL Training, The SGLang Team (2025). https://www.lmsys.org/blog/2025-09-22-sglang-deterministic/
5. Batch Invariance (vLLM documentation), vLLM project (2026). https://github.com/vllm-project/vllm/blob/main/docs/features/batch_invariance.md
6. gensyn-ai/ree: Gensyn Reproducible Execution Environment (GitHub repository), Gensyn (2026). https://github.com/gensyn-ai/ree
7. 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/
8. Building Delphi: Pricing, Settlement, and Agentic Trading, D. Jedamski (2026). https://www.gensyn.ai/blog/building-delphi-pricing-settlement-and-agentic-trading
9. Reproducible Execution Environment (REE) (Gensyn documentation), Gensyn (2026). https://docs.gensyn.ai/tech
10. What is Delphi? (Delphi documentation), Gensyn (2026). https://docs.delphi.fyi/
11. 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
12. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). https://arxiv.org/abs/2506.23706
13. NVIDIA Secure AI with Blackwell and Hopper GPUs (White Paper), NVIDIA (2025). https://docs.nvidia.com/nvidia-secure-ai-with-blackwell-and-hopper-gpus-whitepaper.pdf
14. TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition, J. Chuang et al. (2026). https://tee.fail/
15. Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing, J. De Meulemeester et al. (2026). https://batteringram.eu/
16. RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP, B. Schlüter & S. Shinde (2025). https://rmpocalypse.github.io/
17. SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020), AMD (2025). https://www.amd.com/en/resources/product-security/bulletin/amd-sb-3020.html
18. A primer on secure enclaves, Tinfoil (2026). https://docs.tinfoil.sh/verification/secure-enclave-primer
19. PAL*M: Property Attestation for Large Generative Models, P. Chantasantitam et al. (2026). https://arxiv.org/abs/2601.16199
20. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). https://tinfoil.sh/blog/2026-02-03-proving-model-identity
21. 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
22. [Feature]: Batch Invariant Feature and Performance Optimization (vLLM issue #27433), vLLM project contributors (2025). https://github.com/vllm-project/vllm/issues/27433
23. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). https://amododesign.com/ai-verification/plan-a-sitrep/