# 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-0022&implementations=M-0002:I-0016 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 / Batch-invariant inference kernels (Thinking Machines) | Research demonstration | No published adversarial analysis recorded | Cooperative | None | None | 0 / 0 / 0 | unspecified | unspecified | unspecified | | Side-channel suppression for isolated facilities | Proposed | Published security analysis | Adversarial | Analysis | Retrofit device | 0 / 0 / 0 | not involved | not involved | not involved | ## Claims No claims chosen. ## Mechanisms ### Deterministic and bit-exact inference Open-source GPU kernels from Thinking Machines Lab that make language-model outputs independent of batch size, adopted in vLLM and SGLang for reproducible inference. ([Deterministic and bit-exact inference](https://trustbutveri.fyi/mechanisms/deterministic-inference/)) - Assessment: selected implementation [Batch-invariant inference kernels (Thinking Machines)](https://trustbutveri.fyi/implementations/batch-invariant-inference-kernels/). - Development: Research demonstration (legacy code R2), assessed for exact recomputation of served outputs by a verifier, with a cooperating provider. - Security evidence: No published adversarial analysis recorded. Independent evaluation: unassessed. Formal proof: unassessed. Deployment assurance: unassessed. - Claims in this proposal: none of them. - Threat model: cooperative prover. Hardware: none. Prover cooperation: required. Attack testing: none. 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. ### Side-channel suppression for isolated facilities Shielding, filtering, jamming and inspecting an AI facility to limit hidden physical communication around monitored network links. ([Side-channel suppression for isolated facilities](https://trustbutveri.fyi/mechanisms/side-channel-suppression/)) - Assessment: mechanism family. - Development: Proposed (legacy code R1), assessed for bounding physical covert channels out of a verified enclosure. - 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: 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. Shields and filters a facility; it does not handle model data. ## Properties **Built for an adversarial prover** - Side-channel suppression for isolated facilities **No new hardware needed** - Deterministic and bit-exact inference ## 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** - Side-channel suppression for isolated facilities: Analysis ## Limits **Family finding context** - Context for Batch-invariant inference kernels (Thinking Machines). 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/) [9]. 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 Batch-invariant inference kernels (Thinking Machines). 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/) [9][10]. 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** - Openings for airflow, power and optics weaken shielding (scope limitation, theoretical argument, in Side-channel suppression for isolated facilities; https://trustbutveri.fyi/mechanisms/side-channel-suppression/evidence/flaws/2/) [11]. Cankaya notes that keeping attenuation high while passing high-power airflow, cabling and optical links adds complexity beyond existing shielded-enclosure specifications. **Open questions** - Supply-chain implants may evade inspection (open question, theoretical argument, in Side-channel suppression for isolated facilities; https://trustbutveri.fyi/mechanisms/side-channel-suppression/evidence/flaws/1/) [11]. 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. - Inspection assumptions may not hold (open question, open question, in Side-channel suppression for isolated facilities; https://trustbutveri.fyi/mechanisms/side-channel-suppression/evidence/flaws/3/) [11]. 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: Proposed (legacy code R1), assessed for bounding physical covert channels out of a verified enclosure ## 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. None found. ## Dependencies **Blockers** - Deterministic and bit-exact inference: Batch invariance costs throughput: on Qwen3-8B the improved deterministic build took 42 s against 26 s for vLLM's default, and SGLang reports an average slowdown of 34.35% on its FlashInfer and FlashAttention 3 backends. (performance & compatibility) [1][3] - Deterministic and bit-exact inference: Outputs are identical only while the model, inference implementation and device stay fixed, so provider and verifier must run the same stack. (performance & compatibility) [6] - Side-channel suppression for isolated facilities: No prototype or red-team exists; the design is a first-pass viability study. (adversarial validation) [11] - Side-channel suppression for isolated facilities: Volume costs of TEMPEST-grade power-line filters are uncertain, because existing products are mostly made to order. (performance & compatibility) [11] ## What the verifier sees - Model weights: shown by none; depends on the design for none; hidden by none; not involved in Side-channel suppression for isolated facilities; 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 Side-channel suppression for isolated facilities; unspecified for Deterministic and bit-exact inference. - Training data: shown by none; depends on the design for none; hidden by none; not involved in Side-channel suppression for isolated facilities; 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) - 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) ## Sources 1. Defeating Nondeterminism in LLM Inference, H. He & Thinking Machines Lab (2025). https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/ 2. thinking-machines-lab/batch_invariant_ops (GitHub repository), Thinking Machines Lab (2025). https://github.com/thinking-machines-lab/batch_invariant_ops 3. Towards Deterministic Inference in SGLang and Reproducible RL Training, The SGLang Team (2025). https://www.lmsys.org/blog/2025-09-22-sglang-deterministic/ 4. Batch Invariance (vLLM documentation), vLLM project (2026). https://github.com/vllm-project/vllm/blob/main/docs/features/batch_invariance.md 5. [Feature]: Batch Invariant Feature and Performance Optimization (vLLM issue #27433), vLLM project contributors (2025). https://github.com/vllm-project/vllm/issues/27433 6. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). https://arxiv.org/abs/2511.20621 7. Verde: Verification via Refereed Delegation for Machine Learning Programs, A. Arun et al. (2025). https://arxiv.org/abs/2502.19405 8. EigenAI: Deterministic Inference, Verifiable Results, D. Ribeiro Alves et al. (2026). https://arxiv.org/abs/2602.00182 9. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). https://arxiv.org/abs/2606.00279 10. Hawkeye: Reproducing GPU-Level Non-Determinism, E. Badash et al. (2026). https://proceedings.mlsys.org/paper_files/paper/2026/hash/e217c271a57c365a246b0ad39e668ba8-Abstract-Conference.html 11. 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