# 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-0015,M-0024&implementations=M-0015:I-0011

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 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Memory wiping and proofs of secure erasure / AI 2040 inference-only verification stack | R1 | Adversarial | None | Retrofit device | 0 / 3 / 0 | unspecified | unspecified | unspecified |
| Bounding unexplained information in outputs | R2 | Adversarial | Independent red-team | Retrofit device | 0 / 4 / 0 | depends | depends | not involved |

## Claims

No claims chosen.

## Mechanisms

### Memory wiping and proofs of secure erasure

A proposed retrofit that isolates data-centre inference units, taps their front-end traffic and recomputes random samples to check that only declared inference runs. ([Memory wiping and proofs of secure erasure](https://trustbutveri.fyi/mechanisms/memory-wiping-and-secure-erasure/))

- Assessment: selected implementation [AI 2040 inference-only verification stack](https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/).
- Readiness: R1 Proposed, assessed for showing that retrofitted data centres run only inference.
- Claims in this proposal: none of them.
- Threat model: adversarial prover. Hardware: retrofit device. Prover cooperation: required. Attack testing: none. Category: Isolation & system architectures.
- 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.

### Bounding unexplained information in outputs

Limits the hidden information a facility's outputs can carry by measuring how much of those outputs the declared computation fails to predict. ([Bounding unexplained information in outputs](https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/))

- Assessment: mechanism family.
- Readiness: R2 Demonstrated, assessed for bounding how much hidden information can leave in checked inference outputs.
- Claims in this proposal: none of them.
- Threat model: adversarial prover. Hardware: retrofit device. Prover cooperation: required. Attack testing: independent red-team. Category: Isolation & system architectures.
- What the verifier sees: model weights depends; inputs and outputs depends; training data not involved. Depends on where recomputation runs: in a sealed enclosure, or with zero-knowledge proofs, the verifier need not see the weights or the traffic.


## Properties

**Built for an adversarial prover**

- Memory wiping and proofs of secure erasure
- Bounding unexplained information in outputs


## 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**

- Bounding unexplained information in outputs: Independent red-team


## Limits

**Open significant flaws**

- The recomputation server must be trusted (theoretical argument, in AI 2040 inference-only verification stack; https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/#flaw-1) [1][2][4]. The plan calls the integrity of the recomputation server an extremely important aspect, and its argument that sampling verifies all outputs assumes that the server's computations and outputs can be trusted. The companion page notes that the server sits inside the prover's facility, possibly under the prover's physical control, and that hardening it against integrity attacks needs significant research. Amodo rates recomputation-server security as not on track.
- Spare compute is not verified (theoretical argument, in AI 2040 inference-only verification stack; https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/#flaw-2) [1]. The plan states that it does not verify that spare compute is unused for unapproved workloads, because this seems very challenging. It relies instead on side-channel bounds and memory wipes, so that the only results that persist are verified inference outputs.
- A recomputation family degrades against prompt-controlling adversaries (demonstrated attack, in AI 2040 inference-only verification stack; https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/#flaw-3) [1][2][6][7]. The plan's companion page names DiFR among the recomputation schemes being tested. An independent study found that Gumbel-based inference verification, the family that includes Token-DiFR, leaks roughly twice as many bits per token when the adversary chooses prompts that disrupt the text's structure, across six models of 1 to 32 billion parameters. The slowdown it imposes on a hidden-signalling adversary falls from 146–254 times under benign prompts to 60–118 times. The attack weakens the bound on hidden information in outputs, which the plan relies on to keep undeclared results from leaving.
- Prompt-controlled entropy inflation widens the covert channel (demonstrated attack, in Bounding unexplained information in outputs; https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/#flaw-1) [6][7]. Gumbel-based inference verification tolerates token choices that honest GPU nondeterminism could produce, and the size of that tolerated set grows with the model's output entropy. Kezins, an independent researcher, showed that an adversary who controls the prompt distribution can raise output entropy and roughly double the bits leaked per token. Across six models of 1 to 32 billion parameters, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. Kezins argues that architectures built on the same unexplained-information bound inherit this attack surface, and recommends calibrating tolerances against local token entropy rather than benign traffic.

  Related mechanism: Deterministic and bit-exact inference (R3, not in the proposal). Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata.
- Information the declared computation explains is not bounded (theoretical argument, in Bounding unexplained information in outputs; https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/#flaw-2) [12][13]. The bound limits unexplained bits only. Outputs that the declared computation fully explains can still carry valuable information: a compression study notes that an adversary with inference access can extract more proprietary information per bit than naive transmission allows.
- Channels other than checked outputs are outside the bound (theoretical argument, in Bounding unexplained information in outputs; https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/#flaw-3) [6][11]. The inference-verification scheme treats side channels as out of scope. A low-trust system design argues that suppressing physical covert bandwidth below kilobits per second is much more achievable than aiming for zero, and that a malicious device can leak one bit of information by deliberately outputting a wrong result.

  Related mechanism: Side-channel suppression for isolated facilities (R1, not in the proposal). Physical side channels need separate suppression, which is this mechanism's purpose.
- The facility-level design is untested (open question, in Bounding unexplained information in outputs; https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/#flaw-4) [12]. The compute-verification architecture is described with protocol details, potential attacks and prototyping plans, but no prototype results have been published.

**Family finding context**

- Context for AI 2040 inference-only verification stack; applicability depends on the finding's scope. Memory the wipe cannot reach (open question, in Memory wiping and proofs of secure erasure; https://trustbutveri.fyi/mechanisms/memory-wiping-and-secure-erasure/#flaw-1) [8][9]. Amodo's inventory of a GB200 system lists many memory stores beyond GPU HBM and host DRAM. It notes that SSD controller DRAM sits on a private bus that host commands cannot read or write, and that its optimized algorithm leaves 25 GiB of HBM unattested. It also asks how switch memory could be wiped.
- Context for AI 2040 inference-only verification stack; applicability depends on the finding's scope. Outside help during challenges (theoretical argument, in Memory wiping and proofs of secure erasure; https://trustbutveri.fyi/mechanisms/memory-wiping-and-secure-erasure/#flaw-2) [10][11]. Classic proofs of secure erasure assume the device is isolated during the protocol. Bursuc et al. relax this to a bound on how close a helper can be, enforced by round-trip times. In data centres, remote memory access has round trips of about 1–2 µs, against about 70–200 ns for local DRAM. The MIRI overview therefore says verification depends on ruling out RDMA by latency or physical disconnection.

  Related mechanism: Timed challenge-response and memory-occupation challenges (R2, not in the proposal). Timed challenges bound how far away a helper can be by how quickly it must answer.

  Related mechanism: Bandwidth limits and compartmentalization (R2, not in the proposal). Removing or capping links between groups of accelerators limits remote memory access during a challenge.
- Context for AI 2040 inference-only verification stack; applicability depends on the finding's scope. Gap between erased and total memory (theoretical argument, in Memory wiping and proofs of secure erasure; https://trustbutveri.fyi/mechanisms/memory-wiping-and-secure-erasure/#flaw-3) [10]. Bursuc et al. note that memory left between the erased region and the device's full memory could hold data, and that their bounds are tighter only against a restricted adversary.

**Not yet demonstrated**

- Memory wiping and proofs of secure erasure: R1 Proposed, assessed for showing that retrofitted data centres run only inference


## 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.

- **Deterministic and bit-exact inference** (R3 In production, assessed for reproducing open-model inference from receipts in Gensyn's information-market service)
  - Bears on the open significant flaw "Prompt-controlled entropy inflation widens the covert channel" in Bounding unexplained information in outputs. Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata.
  - Bounding unexplained information in outputs waits on it: Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata.
- **Side-channel suppression for isolated facilities** (R1 Proposed, assessed for bounding physical covert channels out of a verified enclosure)
  - Bears on the open significant flaw "Channels other than checked outputs are outside the bound" in Bounding unexplained information in outputs. Physical side channels need separate suppression, which is this mechanism's purpose.
  - Memory wiping and proofs of secure erasure waits on it: There is no plan yet for quickly scaling side-channel defences on a frontier cluster; only early theoretical pieces exist.
  - Bounding unexplained information in outputs waits on it: Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target.
- **Bandwidth limits and compartmentalization** (R2 Demonstrated, assessed for monitoring inter-node traffic with operator-run software on four GPUs)
  - Bounding unexplained information in outputs waits on it: The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound.
- **Tamper evidence for verifier devices** (R2 Demonstrated, assessed for detecting probing of proposed verifier hardware, using server and electronics prototypes as evidence)
  - Memory wiping and proofs of secure erasure waits on it: Checking that taps are correctly installed and stay in place at scale is not a solved problem, and hardening the recomputation server inside the prover's facility needs significant research.
- **Network taps and certifiers** (R1 Proposed, assessed for committing a complete record of cluster traffic, so declared inference can be checked)
  - Memory wiping and proofs of secure erasure waits on it: Passive optical taps work at 400G, but the 800G and 1600G line rates now arriving in data centres are undemonstrated.
  - Bounding unexplained information in outputs depends on it.
- **Whole-workload recomputation (reproducible packets)** (R1 Proposed, assessed for recomputing whole workloads to show a cluster runs only declared inference)
  - Memory wiping and proofs of secure erasure waits on it: A fully reproducible inference stack needs substantial software and tooling, and per-packet network reproducibility may need considerable software, firmware and possibly hardware work.
- **Sampled inference recomputation** (R3 In production, assessed for checking untrusted workers' activations against the declared model, prompt and precision)
  - Memory wiping and proofs of secure erasure depends on it.
  - Bounding unexplained information in outputs depends on it.


## Dependencies

**Missing prerequisites**

- Sampled inference recomputation (R3 In production, assessed for checking untrusted workers' activations against the declared model, prompt and precision), needed by Memory wiping and proofs of secure erasure and Bounding unexplained information in outputs
- Whole-workload recomputation (reproducible packets) (R1 Proposed, assessed for recomputing whole workloads to show a cluster runs only declared inference), needed by Memory wiping and proofs of secure erasure
- Bandwidth limits and compartmentalization (R2 Demonstrated, assessed for monitoring inter-node traffic with operator-run software on four GPUs), needed by Bounding unexplained information in outputs
- Side-channel suppression for isolated facilities (R1 Proposed, assessed for bounding physical covert channels out of a verified enclosure), needed by Bounding unexplained information in outputs
- Network taps and certifiers (R1 Proposed, assessed for committing a complete record of cluster traffic, so declared inference can be checked), needed by Bounding unexplained information in outputs

**Shared foundations**

- Sampled inference recomputation, relied on by Memory wiping and proofs of secure erasure and Bounding unexplained information in outputs
- Network taps and certifiers, relied on by Memory wiping and proofs of secure erasure and Bounding unexplained information in outputs
- Side-channel suppression for isolated facilities, relied on by Memory wiping and proofs of secure erasure and Bounding unexplained information in outputs

**Blockers**

- Memory wiping and proofs of secure erasure: A fully reproducible inference stack needs substantial software and tooling, and per-packet network reproducibility may need considerable software, firmware and possibly hardware work. (performance & compatibility; waits on Whole-workload recomputation (reproducible packets)) [2]
- Memory wiping and proofs of secure erasure: Passive optical taps work at 400G, but the 800G and 1600G line rates now arriving in data centres are undemonstrated. (performance & compatibility; waits on Network taps and certifiers) [2]
- Memory wiping and proofs of secure erasure: Checking that taps are correctly installed and stay in place at scale is not a solved problem, and hardening the recomputation server inside the prover's facility needs significant research. (hardware trust; waits on Tamper evidence for verifier devices) [2][4]
- Memory wiping and proofs of secure erasure: There is no plan yet for quickly scaling side-channel defences on a frontier cluster; only early theoretical pieces exist. (coverage & hidden compute; waits on Side-channel suppression for isolated facilities) [2]
- Memory wiping and proofs of secure erasure: Memory wiping may use existing algorithms, but hardware testing is at an early stage. (coverage & hidden compute; waits on Memory wiping and proofs of secure erasure) [2]
- Memory wiping and proofs of secure erasure: Robust red-teaming of recomputation schemes has not started, and most algorithm development remains academic. (adversarial validation) [2][4]
- Bounding unexplained information in outputs: The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound. (coverage & hidden compute; waits on Bandwidth limits and compartmentalization) [12]
- Bounding unexplained information in outputs: Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target. (coverage & hidden compute; waits on Side-channel suppression for isolated facilities) [6][11]
- Bounding unexplained information in outputs: Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata. (protocol soundness; waits on Deterministic and bit-exact inference) [7][11]
- Bounding unexplained information in outputs: Recomputation over confidential weights and inputs needs a protected setting: prover recomputation in a verifier-controlled enclosure, verifier recomputation in a prover-controlled enclosure, or zero-knowledge proofs. (privacy & leakage) [12]
- Bounding unexplained information in outputs: No prototype of the facility-level architecture exists to red-team. (adversarial validation) [12]


## What the verifier sees

- Model weights: shown by none; depends on the design for Bounding unexplained information in outputs; hidden by none; not involved in none; unspecified for Memory wiping and proofs of secure erasure.
- Inputs and outputs: shown by none; depends on the design for Bounding unexplained information in outputs; hidden by none; not involved in none; unspecified for Memory wiping and proofs of secure erasure.
- Training data: shown by none; depends on the design for none; hidden by none; not involved in Bounding unexplained information in outputs; unspecified for Memory wiping and proofs of secure erasure.

## Implementations

- Memory wiping and proofs of secure erasure: [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)
- Bounding unexplained information in outputs: none on the map

## Sources

1. Verification Plan, R. Dean (2026). https://ai-2040.com/supplements/verification-plan
2. Get Involved in Verification, AI Futures Project (2026). https://ai-2040.com/supplements/verification-plan/get-involved
3. Verifying international AI deals: Plan A, the state-of-play, and what you can do to help, T. Milton et al. (2026). https://amodo.substack.com/p/verifying-international-ai-deals
4. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). https://amododesign.com/ai-verification/plan-a-sitrep/
5. Fitting a Network TAP to our Inference Verification Prototype, Amodo Design (2026). https://amododesign.com/notes/2026-09-15-network-tap-inference-verification/
6. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). https://arxiv.org/abs/2511.02620
7. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). https://arxiv.org/abs/2608.23375
8. Memory Wipes - Performance Analysis, Amodo Design (2026). https://amododesign.com/notes/2026-07-01-memory-wiping/
9. Improving Disk Wiping Speed for Memory Wipes, Amodo Design (2026). https://amododesign.com/notes/2026-09-14-disk-wiping-speed/
10. Software-Based Memory Erasure with Relaxed Isolation Requirements, S. Bursuc et al. (2024). https://ieeexplore.ieee.org/document/10664348/
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. Verifying AI Compute by Bounding Unexplained Information Exfiltration, J. Petrie & Y. Mühlhäuser (2026). https://openreview.net/forum?id=qtgG5HZSsk
13. Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains, R. Rinberg et al. (2026). https://arxiv.org/abs/2604.02343