Proposal Explorer

Add claims to see which ones the mechanisms address.

Built for an adversarial prover

Sampled inference recomputation and Bounding unexplained information in outputs

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.

• Bounding unexplained information in outputs: Independent red-team

Family findings

• Sampled inference recomputation

  Context for AI 2040 inference-only verification stack. 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.

  • Tolerance for numerical noise leaves a covert channel in Sampled inference recomputation

    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. ^{6 7 8}

    Known failure · Demonstrated attack · Significant · Open. On the record

    Related mechanism Operational use Deterministic and bit-exact inference: Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration. A pointer, not evidence that this failure is mitigated. Add

  • Only recorded traffic is checked in Sampled inference recomputation

    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. ^{6 9}

    Scope limitation · Theoretical argument. On the record

    Related mechanism Proposed Network taps and certifiers: 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. A pointer, not evidence that this failure is mitigated. Add

  • Some inference optimizations are not covered in Sampled inference recomputation

    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. ^{10 11}

    Known failure · Theoretical argument · Significant · Open. On the record

  • Mixed hardware widens the honest baseline in Sampled inference recomputation

    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. ¹¹

    Known failure · Open question · Minor · Open. On the record

Open significant failures

2 failures in 2 mechanisms

• A recomputation family degrades against prompt-controlling adversaries in AI 2040 inference-only verification stack

  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. ^{1 2 6 7}

  Known failure · Demonstrated attack · Significant · Open. On the record

• Prompt-controlled entropy inflation widens the covert channel in Bounding unexplained information in outputs

  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. ^{6 7}

  Known failure · Demonstrated attack · Significant · Open. On the record

  Related mechanism Operational use Deterministic and bit-exact inference: 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. A pointer, not evidence that this failure is mitigated. Add

Scope limitations

• The recomputation server must be trusted in AI 2040 inference-only verification stack

  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. ^{1 2 4}

  Scope limitation · Theoretical argument. On the record

• Spare compute is not verified in AI 2040 inference-only verification stack

  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. ¹

  Scope limitation · Theoretical argument. On the record

• Information the declared computation explains is not bounded in Bounding unexplained information in outputs

  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. ^{12 13}

  Scope limitation · Theoretical argument. On the record

• Channels other than checked outputs are outside the bound in Bounding unexplained information in outputs

  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. ^{6 14}

  Scope limitation · Theoretical argument. On the record

  Related mechanism Proposed Side-channel suppression for isolated facilities: Physical side channels need separate suppression, which is this mechanism's purpose. A pointer, not evidence that this failure is mitigated. Add

Open questions

• The facility-level design is untested in Bounding unexplained information in outputs

  The compute-verification architecture is described with protocol details, potential attacks and prototyping plans, but no prototype results have been published. ¹²

  Open question · Open question. On the record

Not yet demonstrated

Proposed Sampled inference recomputation

Mechanisms on the map that are not in the proposal. Pointers, not recommendations. ?

• Operational use Deterministic and bit-exact inference Add
  • Bears on the open significant failure “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.
• Research demo Bandwidth limits and compartmentalization Add
  • 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.
• Research demo Tamper evidence for verifier devices Add
  • Sampled inference recomputation 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.
• Proposed Memory wiping and proofs of secure erasure Add
  • Sampled inference recomputation waits on it. Memory wiping may use existing algorithms, but hardware testing is at an early stage.
• Proposed Network taps and certifiers Add
  • Sampled inference recomputation 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.
• Proposed Side-channel suppression for isolated facilities Add
  • Sampled inference recomputation 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.
• Proposed Whole-workload recomputation (reproducible packets) Add
  • Sampled inference recomputation 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.

Missing prerequisites

• Proposed Whole-workload recomputation (reproducible packets) needed by Sampled inference recomputation Add
• Research demo Bandwidth limits and compartmentalization needed by Bounding unexplained information in outputs Add
• Proposed Side-channel suppression for isolated facilities needed by Bounding unexplained information in outputs Add
• Proposed Network taps and certifiers needed by Bounding unexplained information in outputs Add

Shared foundations

• Network taps and certifiers relied on by Sampled inference recomputation and Bounding unexplained information in outputs
• Side-channel suppression for isolated facilities relied on by Sampled inference recomputation and Bounding unexplained information in outputs

Blockers

11 blockers recorded

• Sampled inference recomputation
  • 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
  • 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
  • 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}
  • 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 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
  • 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
  • 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 14}
  • 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 14}
  • 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
  • No prototype of the facility-level architecture exists to red-team. Adversarial validation ¹²

From the family or selected implementation's record. ?

Model weights

Depends on the design for Bounding unexplained information in outputs.

Unspecified for Sampled inference recomputation. Check the implementation record.

Inputs and outputs

Depends on the design for Bounding unexplained information in outputs.

Unspecified for Sampled inference recomputation. Check the implementation record.

Training data

Not involved: Bounding unexplained information in outputs.

Unspecified for Sampled inference recomputation. Check the implementation record.

Sampled inference recomputation

• Proposed AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• Research demo DiFR (Divergence From Reference) Research prototype
• Proposed Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
• Proposed SASH confidential network logger Research prototype, Singapore AI Safety Hub (SASH)
• Operational use TOPLOC Open-source project, Prime Intellect

Bounding unexplained information in outputs

None on the map

1. Verification Plan, R. Dean (2026). Original
2. Get Involved in Verification, AI Futures Project (2026). Original
3. Verifying international AI deals: Plan A, the state-of-play, and what you can do to help, T. Milton et al. (2026). Original
4. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original
5. Fitting a Network TAP to our Inference Verification Prototype, Amodo Design (2026). Original
6. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
7. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
8. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
9. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). Original
10. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). Original
11. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). Original
12. Verifying AI Compute by Bounding Unexplained Information Exfiltration, J. Petrie & Y. Mühlhäuser (2026). Original
13. Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains, R. Rinberg et al. (2026). Original
14. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original