# 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-0022,M-0001&implementations=M-0001:I-0002 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 | | --- | --- | --- | --- | --- | --- | --- | --- | --- | | Side-channel suppression for isolated facilities | R1 | Adversarial | Analysis | Retrofit device | 0 / 3 / 0 | not involved | not involved | not involved | | Sampled inference recomputation / DiFR (Divergence From Reference) | R2 | Adversarial | Analysis | None | 0 / 2 / 1 | unspecified | unspecified | unspecified | ## Claims No claims chosen. ## Mechanisms ### 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. - Readiness: R1 Proposed, assessed for bounding physical covert channels out of a verified enclosure. - 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. ### Sampled inference recomputation DiFR checks that an inference provider ran its declared model by comparing output tokens or activations with a trusted re-run using the same random seed. ([Sampled inference recomputation](https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/)) - Assessment: selected implementation [DiFR (Divergence From Reference)](https://trustbutveri.fyi/implementations/difr/). - Readiness: R2 Demonstrated, assessed for checking that outputs match the declared model, precision and sampling settings. - 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. ## Properties **Built for an adversarial prover** - Side-channel suppression for isolated facilities - Sampled inference recomputation **No new hardware needed** - 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** - Side-channel suppression for isolated facilities: Analysis - Sampled inference recomputation / DiFR (Divergence From Reference): Analysis ## Limits **Open significant flaws** - Supply-chain implants may evade inspection (theoretical argument, in Side-channel suppression for isolated facilities; https://trustbutveri.fyi/mechanisms/side-channel-suppression/#flaw-1) [1]. 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. - Openings for airflow, power and optics weaken shielding (theoretical argument, in Side-channel suppression for isolated facilities; https://trustbutveri.fyi/mechanisms/side-channel-suppression/#flaw-2) [1]. Cankaya notes that keeping attenuation high while passing high-power airflow, cabling and optical links adds complexity beyond existing shielded-enclosure specifications. - Inspection assumptions may not hold (open question, in Side-channel suppression for isolated facilities; https://trustbutveri.fyi/mechanisms/side-channel-suppression/#flaw-3) [1]. 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. - Statistical tolerance leaves a covert channel (demonstrated attack, in DiFR (Divergence From Reference); https://trustbutveri.fyi/implementations/difr/#flaw-1) [3][8][10]. Statistical schemes can put an upper bound on an adversary's covert bandwidth, but cannot close it. In the companion exfiltration study, the detector cut exfiltratable information to under 0.5% under benign prompt traffic. It did not cut it to zero. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study attacked that detector, which uses the same Gumbel-margin statistic. An adversary who controls the prompts roughly doubled the bits leaked per token. Across six models, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target DiFR's check that outputs match the declared configuration. - Speculative decoding and multi-model sampling not evaluated (open question, in DiFR (Divergence From Reference); https://trustbutveri.fyi/implementations/difr/#flaw-3) [2]. The algorithms and experiments cover sampling from a single LLM. Speculative decoding was not evaluated. The authors sketch an extension to one speculative-decoding algorithm, without experiments. They note that other variants would need modified verification and extra metadata. **Family finding context** - Context for DiFR (Divergence From Reference); applicability depends on the finding's scope. Tolerance for numerical noise leaves a covert channel (demonstrated attack, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-1) [3][8][10]. 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, not in the proposal). Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration. - Context for DiFR (Divergence From Reference); applicability depends on the finding's scope. Only recorded traffic is checked (theoretical argument, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-2) [3][11]. 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. - Context for DiFR (Divergence From Reference); applicability depends on the finding's scope. Some inference optimizations are not covered (theoretical argument, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-3) [2][12]. 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. - Context for DiFR (Divergence From Reference); applicability depends on the finding's scope. Mixed hardware widens the honest baseline (open question, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-4) [2]. 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. **Open minor flaws** - Mixed hardware widens the honest baseline (open question, in DiFR (Divergence From Reference); https://trustbutveri.fyi/implementations/difr/#flaw-2) [2]. For Qwen3-30B-A3B, pooling honest runs across A100 and H200 GPUs and parallelism setups broadened the honest score distribution. Token-DiFR then failed 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 did. The authors report that matched provider and verifier environments, or pooling that weights rare large deviations, restore detection. **Not yet demonstrated** - Side-channel suppression for isolated facilities: R1 Proposed, 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 flaw or a dependency. Pointers, not recommendations: each brings its own readiness level and flaws, and none is claimed to close a flaw. None found. ## Dependencies **Blockers** - Side-channel suppression for isolated facilities: No prototype or red-team exists; the design is a first-pass viability study. (adversarial validation) [1] - 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) [1] - Sampled inference recomputation: The verifier needs the model weights, so outsiders cannot use the method to verify providers of closed-weights models. (privacy & leakage) [2] - Sampled inference recomputation: The verifier must know and match the provider's sampling procedure, and in one prototype a sampling mismatch in a newer vLLM version produced large spurious logit differences. (performance & compatibility) [2][5] - Sampled inference recomputation: No independent red-team of DiFR's consistency check has been published, Amodo rates recomputation red-teaming 'not started', and the one independent attack study targets an exfiltration detector built on the same statistic. (adversarial validation) [7][8] ## 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 Sampled inference recomputation. - 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 Sampled inference recomputation. - 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 Sampled inference recomputation. ## Implementations - 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) - 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. 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 2. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). https://arxiv.org/abs/2511.20621 3. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). https://arxiv.org/abs/2511.02620 4. adamkarvonen/difr (GitHub repository), A. Karvonen (2025). https://github.com/adamkarvonen/difr 5. Scaling Recomputation Inference Verification, Amodo Design (2026). https://amododesign.com/notes/2026-09-02-scaling-recomputation-inference-verification/ 6. Amodo-Design/Inference-Recomputation-Prototype (GitHub repository), Amodo Design (2026). https://github.com/Amodo-Design/Inference-Recomputation-Prototype 7. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). https://amododesign.com/ai-verification/plan-a-sitrep/ 8. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). https://arxiv.org/abs/2608.23375 9. An Inference Verification Prototype — Stage 1, Amodo Design (2026). https://amododesign.com/notes/2026-06-29-inference-verification-prototype/ 10. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). https://arxiv.org/abs/2606.00279 11. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). https://amododesign.com/notes/2026-06-23-verification-algorithms/ 12. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). https://proceedings.mlr.press/v267/ong25a.html