# 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-0002:I-0015

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 / Verde and RepOps (Gensyn) | Operational use | Published security analysis | Adversarial | Analysis | None | 0 / 0 / 0 | unspecified | unspecified | unspecified |
| Hardware-attested weight binding | Operational use | Published attack testing | Semi-trusted | Independent red-team | Existing features | 1 / 0 / 0 | hidden | unspecified | not involved |

## Claims

No claims chosen.

## Mechanisms

### Deterministic and bit-exact inference

Gensyn's system for checking machine-learning jobs given to untrusted providers, which settles disagreements by re-running one operation with operators that give bit-identical results across hardware. ([Deterministic and bit-exact inference](https://trustbutveri.fyi/mechanisms/deterministic-inference/))

- Assessment: selected implementation [Verde and RepOps (Gensyn)](https://trustbutveri.fyi/implementations/gensyn-verde-repops/).
- Development: Operational use (legacy code R3), assessed for reproducing declared-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 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.

### Hardware-attested weight binding

Checks that a hardware enclave serves committed model weights, by attesting software that tests the weights against a hash commitment when they are read. ([Hardware-attested weight binding](https://trustbutveri.fyi/mechanisms/model-identity-attestation/))

- Assessment: mechanism family.
- Development: Operational use (legacy code R3), assessed for hardware-attested weight binding showing users that a service runs its committed weights.
- Security evidence: Published attack testing. 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: independent red-team. Category: Cryptographic & computational.
- What the verifier sees: model weights hidden; inputs and outputs unspecified; training data not involved. Verifiers check a hash commitment to the weights, carried in a hardware attestation, and need no access to the weights themselves. The mechanism does not specify whether prompts and outputs are disclosed to a verifier. It involves no training data.


## Properties

**Operational use**

- Deterministic and bit-exact inference: Operational use (legacy code R3), assessed for reproducing declared-model inference from receipts in Gensyn's information-market service
- Hardware-attested weight binding: Operational use (legacy code R3), assessed for hardware-attested weight binding showing users that a service runs its committed weights

**Built for an adversarial prover**

- Deterministic and bit-exact inference

**No new hardware needed**

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

**Failures since mitigated**

- Launch-state attestation does not by itself cover weights loaded later (in Hardware-attested weight binding) [10][20]


## 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 / Verde and RepOps (Gensyn): Analysis
- Hardware-attested weight binding: Independent red-team


## Limits

**Open critical failures**

- 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/) [11][12][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.

**Family finding context**

- Context for Verde and RepOps (Gensyn). 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. Some kernels remain genuinely nondeterministic (scope limitation, open question, in Deterministic and bit-exact inference; https://trustbutveri.fyi/mechanisms/deterministic-inference/evidence/flaws/1/) [8]. 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.
- Context for Verde and RepOps (Gensyn). 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. 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/) [8][9]. 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.

**Scope limitations**

- 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/) [10][21]. 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.


## 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.

- **Hardware-enabled guarantees (flexHEG) and guarantee processors** (Proposed (legacy code R1), assessed for checking and enforcing training-compute limits on chips, against adversaries up to states)
  - Bears on the open critical failure "Underlying attestation can be forged or relayed" in Hardware-attested weight binding. A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically.
- **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: Attestation that resists physical attackers, for the enclave variant.


## 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: Reproducibility costs throughput: RepOps added 98% to Llama-8B inference time on an A100 in the paper, and Gensyn reports a threefold cut in REE's reproducible-mode overhead without absolute figures. (performance & compatibility) [1][4]
- Deterministic and bit-exact inference: The providers who re-run a job and the referee need the model and data, and the guarantee holds only if at least one provider is honest. (privacy & leakage) [1]
- Hardware-attested weight binding: Attestation that resists physical attackers, for the enclave variant. (hardware trust; waits on TEE remote attestation for AI workloads) [16]


## What the verifier sees

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

## 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. Verde: Verification via Refereed Delegation for Machine Learning Programs, A. Arun et al. (2025). https://arxiv.org/abs/2502.19405
2. Verde Verification System In Production, O. Ersoy (2025). https://www.gensyn.ai/research/verde-verification-system-in-production
3. Introducing Judge, Gensyn (2025). https://www.gensyn.ai/news/introducing-judge
4. gensyn-ai/ree: Gensyn Reproducible Execution Environment (GitHub repository), Gensyn (2026). https://github.com/gensyn-ai/ree
5. Building Delphi: Pricing, Settlement, and Agentic Trading, D. Jedamski (2026). https://www.gensyn.ai/blog/building-delphi-pricing-settlement-and-agentic-trading
6. Reproducible Execution Environment (REE) (Gensyn documentation), Gensyn (2026). https://docs.gensyn.ai/tech
7. What is Delphi? (Delphi documentation), Gensyn (2026). https://docs.delphi.fyi/
8. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). https://arxiv.org/abs/2606.00279
9. Hawkeye: Reproducing GPU-Level Non-Determinism, E. Badash et al. (2026). https://proceedings.mlsys.org/paper_files/paper/2026/hash/e217c271a57c365a246b0ad39e668ba8-Abstract-Conference.html
10. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). https://tinfoil.sh/blog/2026-02-03-proving-model-identity
11. PAL*M: Property Attestation for Large Generative Models, P. Chantasantitam et al. (2026). https://arxiv.org/abs/2601.16199
12. A primer on secure enclaves, Tinfoil (2026). https://docs.tinfoil.sh/verification/secure-enclave-primer
13. Backend infrastructure, Tinfoil (2026). https://docs.tinfoil.sh/verification/attestation-architecture
14. How verification works in Tinfoil, Tinfoil (2026). https://docs.tinfoil.sh/verification/verification-in-tinfoil
15. modelwrap: Reproducible dm-verity read-only image of Huggingface models, Tinfoil (2026). https://github.com/tinfoilsh/modelwrap
16. TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition, J. Chuang et al. (2026). https://tee.fail/
17. Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing, J. De Meulemeester et al. (2026). https://batteringram.eu/
18. RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP, B. Schlüter & S. Shinde (2025). https://rmpocalypse.github.io/
19. SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020), AMD (2025). https://www.amd.com/en/resources/product-security/bulletin/amd-sb-3020.html
20. 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
21. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). https://arxiv.org/abs/2506.23706