Proposal Explorer

Add claims to see which ones the mechanisms address.

Operational use

• Operational use Sampled inference recomputation for checking untrusted workers' activations against the declared model, prompt and precision

Built for an adversarial prover

Bandwidth limits and compartmentalization, Whole-workload recomputation (reproducible packets), Sampled inference recomputation and Tamper evidence for verifier devices

No new hardware needed

Sampled inference recomputation

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.

• Bandwidth limits and compartmentalization: Analysis
• Sampled inference recomputation: Analysis
• Tamper evidence for verifier devices: Analysis

Open significant failures

6 failures in 3 mechanisms

• Operator control of pod routing collapses the bound in Bandwidth limits and compartmentalization

  Lucid's analysis finds that if the operator can freely assign pods to routers, it could dedicate a whole cell of 100 or more pods to one pipeline stage. The bound then falls to about 90–220x uncompressed and as low as about 25x with compression. The proposed mitigation, auditor-controlled random assignment that is periodically re-randomized, has not been implemented. ²

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

• Parallel scale-up switches are hard enforcement points in Bandwidth limits and compartmentalization

  In GB200 topologies, GPUs reach GPUs in other nodes through NVSwitches without a NIC on the path. Amodo notes that limits are hard to enforce there because many switches work in parallel, so compromising one or two would bypass the limit. ⁵

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

• 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. ^{13 19 22}

  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

• 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. ^{14 15}

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

• Seals are often defeated with simple methods in Tamper evidence for verifier devices

  Published defeats of general security seals. They warn about proposed verifier-device seals, but do not demonstrate defeat of an AI verification enclosure or sensor.

  In 1996 a Los Alamos vulnerability assessment defeated all 94 security seals it examined, with 132 defeats in total, using rapid, inexpensive, low-tech methods. It found that seal cost did not predict security. In 2001 Johnston reported that high-tech seals are often easier to defeat than low-tech ones. ^{29 30}

  Known failure · Demonstrated attack · Significant · Open · Mechanism-class evidence. On the record

• Attack classes outside published models in Tamper evidence for verifier devices

  The radio compensation result is emulated using measured channel data under a known-reference attacker model. It is not a physical bypass demonstration against an AI verifier enclosure.

  The authors of the batteryless cover say they cannot assess chemical-solvent attacks, which exceed their expertise, and deem cover removal impractical. Anti-Tamper Radio's reference can drift as the environment or measurement system ages; the authors suggest gradually renewing the reference. A 2025 follow-up by some of the same authors shows, by emulation on measured channel data, that an attacker who knows the reference channel and the needle's effect on it could inject a signal that cancels the change caused by a needle insertion. It proposes a reconfigurable intelligent surface that randomizes the channel as a countermeasure. ^{23 24 31}

  Known failure · Open question · Significant · Open · Mechanism-class evidence. On the record

Scope limitations

• Undeclared local storage raises per-pod capacity in Bandwidth limits and compartmentalization

  More memory or storage per pod helps an adversary. Lucid requires per-pod storage to be declared, capped and physically inspected. ²

  Scope limitation · Theoretical argument. On the record

• Training within one pod is not covered in Bandwidth limits and compartmentalization

  Lucid's bounds concern pre-training models larger than the pods are sized for. Training models that fit in one pod, fine-tuning and reinforcement-learning post-training within one pod are outside the modelled threat. ²

  Scope limitation · Open question. On the record

• Spare compute is outside the scheme in Whole-workload recomputation (reproducible packets)

  The plan states that it does not verify that spare compute is not used for unapproved workloads, because this seems very challenging. Recomputation checks the correctness of declared work, not its completeness. ^{1 8}

  Scope limitation · Theoretical argument. On the record

  Related mechanism Proposed Proofs of useful work for capacity accounting: Proposed as one input to accounting for spare capacity on declared hardware. 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. ^{8 13}

  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

• Security depends on inspection protocols in Tamper evidence for verifier devices

  An inspection and protocol requirement drawn from safeguards and enclosure studies, not a reported break of a deployed AI verifier.

  Johnston argues that a seal is no better than the protocols for using it, and that inspectors are usually given little useful information on how to detect tampering. The Sandia survey notes that larger enclosures are hard to inspect fully and that sensor data must be authenticated. ^{28 30}

  Scope limitation · Theoretical argument · Mechanism-class evidence. On the record

Open questions

• Low-communication training reduces the bandwidth training needs in Bandwidth limits and compartmentalization

  DiLoCo matched fully synchronous training on 8 workers while communicating 500 times less. Rahman writes that this family of methods theoretically allows large-scale training with less than 100 Mbps. Lucid includes these methods in its bounds, but notes that extreme activation compression, architectures with unusually small inter-layer widths, or modular paradigms could erode the margin. ^{2 6 7}

  Open question · Theoretical argument. On the record

• Non-compliant work could be encoded inside compliant-looking packets in Whole-workload recomputation (reproducible packets)

  The plan notes that an AI company might try to encode a non-compliant workload inside a workload that looks compliant on the surface. ¹

  Open question · Theoretical argument. On the record

Open minor failures

1 mechanism with minor failures

• 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. ¹⁴

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

Not yet demonstrated

Proposed Whole-workload recomputation (reproducible packets)

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 “Tolerance for numerical noise leaves a covert channel” in Sampled inference recomputation. Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration.
  • Whole-workload recomputation (reproducible packets) waits on it. Workloads are not reproducible by default, and achieving reproducibility may cost performance.
• Proposed Network taps and certifiers Add
  • Bandwidth limits and compartmentalization waits on it. The verifier must know that all traffic leaving a pod crosses the capped, monitored links.
  • Whole-workload recomputation (reproducible packets) waits on it. All traffic must reach the recomputation server via network taps, and the server's integrity is critical.
  • Sampled inference recomputation waits on it. In tap-based retrofit designs, recording all inference traffic needs network taps and recomputation servers that can ingest it, in the worst case one recomputation-server network interface per inference front-end interface.

Missing prerequisites

• Operational use Deterministic and bit-exact inference needed by Whole-workload recomputation (reproducible packets) Add
• Proposed Network taps and certifiers needed by Whole-workload recomputation (reproducible packets) Add

Shared foundations

• Network taps and certifiers relied on by Bandwidth limits and compartmentalization, Whole-workload recomputation (reproducible packets) and Sampled inference recomputation

Blockers

17 blockers recorded

• Bandwidth limits and compartmentalization
  • No cap that a verifier can check has been implemented or red-teamed. Adversarial validation ²
  • The verifier must know that all traffic leaving a pod crosses the capped, monitored links. Coverage & hidden compute. Waits on Network taps and certifiers ³
  • Shaping devices and routing assignments must be trusted by both parties; Amodo has not yet fully analysed resilience to a compromised DPU. Hardware trust. Waits on Tamper evidence for verifier devices ^{2 5}
  • Advances in low-communication training could shrink the margin that the cap enforces. Capacity bounds ^{2 6 7}
• Whole-workload recomputation (reproducible packets)
  • Workloads are not reproducible by default, and achieving reproducibility may cost performance. Performance & compatibility. Waits on Deterministic and bit-exact inference ¹
  • Network packets are not individually reproducible by default; making them so may need considerable software, firmware and hardware work. Amodo rates this 'not on track'. Performance & compatibility ¹⁰
  • All traffic must reach the recomputation server via network taps, and the server's integrity is critical. Hardware trust. Waits on Network taps and certifiers ^{1 10}
  • Recomputing training steps needs checkpoints: writing one at every step would cost more than 100% overhead, so Amodo's design needs a spare data-parallel replica that tracks the weights instead. Performance & compatibility ⁸
• Sampled inference recomputation
  • In tap-based retrofit designs, recording all inference traffic needs network taps and recomputation servers that can ingest it, in the worst case one recomputation-server network interface per inference front-end interface. Coverage & hidden compute. Waits on Network taps and certifiers ^{1 10}
  • In retrofit designs, the recomputation server must sit inside the prover's data centre, possibly under the prover's physical control, and still be protected from a compromised provider, which Amodo rates 'not on track'. Hardware trust ^{10 13}
  • No independent red-team of a recomputation consistency check has been published (the one independent attack study targets the weight-exfiltration bound), and Amodo rates recomputation red-teaming 'not started'. Adversarial validation ^{10 19}
  • Tolerance-based checks need calibration on trusted hardware and exact knowledge of the provider's sampling procedure, and in one prototype a sampling-implementation mismatch produced large spurious differences. Performance & compatibility ^{9 14}
  • The verifier needs the model weights, so checking a closed-weights model requires a trusted, confidential recomputation environment, which the retrofit designs place inside the prover's facility. Privacy & leakage ^{3 8 14}
• Tamper evidence for verifier devices
  • No tamper-evident enclosure has been designed for AI verifier hardware at retrofit scale. Hardware trust ³
  • Battery-backed designs add bulk, limit operating temperature (+10 °C to +35 °C for the IBM 4765) and complicate transport. Performance & compatibility ²⁴
  • Active monitoring needs power, and visual inspection of large enclosures faces access limits. Access & governance ²⁸
  • No evaluation has been published in the AI verification setting. Adversarial validation ³

From the family or selected implementation's record. ?

Model weights

Depends on the design for Whole-workload recomputation (reproducible packets) and Sampled inference recomputation.

Not involved: Bandwidth limits and compartmentalization and Tamper evidence for verifier devices.

Inputs and outputs

Depends on the design for Whole-workload recomputation (reproducible packets) and Sampled inference recomputation.

Not involved: Bandwidth limits and compartmentalization and Tamper evidence for verifier devices.

Training data

Depends on the design for Whole-workload recomputation (reproducible packets).

Not involved: Bandwidth limits and compartmentalization, Sampled inference recomputation and Tamper evidence for verifier devices.

Bandwidth limits and compartmentalization

• Proposed AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• Proposed RAND secure inference data center (SIDC) design Proposed architecture, RAND

Whole-workload recomputation (reproducible packets)

• Proposed AI 2040 inference-only verification stack Proposed architecture, AI Futures Project

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

Tamper evidence for verifier devices

• Proposed AI 2040 inference-only verification stack Proposed architecture, AI Futures Project

1. Verification Plan, R. Dean (2026). Original
2. Traffic Shaping for Workload Classification, Lucid Computing (2026). Original
3. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
4. De-risking Interconnect Limits for AI Verification, A. Scher et al. (2026). Original
5. The Tray as a Bandwidth Boundary, Amodo Design (2026). Original
6. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). Original
7. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). Original
8. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). Original
9. Scaling Recomputation Inference Verification, Amodo Design (2026). Original
10. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original
11. Get Involved in Verification, AI Futures Project (2026). Original
12. Proof-of-Learning is Currently More Broken Than You Think, C. Fang et al. (2023). Original
13. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
14. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). Original
15. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). Original
16. PrimeIntellect-ai/toploc (GitHub repository), Prime Intellect (2025). Original
17. INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning, Prime Intellect Team et al. (2025). Original
18. adamkarvonen/difr (GitHub repository), A. Karvonen (2025). Original
19. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
20. SYNTHETIC-2 Release: Four Million Collaboratively Generated Reasoning Traces, Prime Intellect (2025). Original
21. An Inference Verification Prototype — Stage 1, Amodo Design (2026). Original
22. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
23. Anti-Tamper Radio: System-Level Tamper Detection for Computing Systems, P. Staat et al. (2022). Original
24. Secure Physical Enclosures from Covers with Tamper-Resistance, V. Immler et al. (2019). Original
25. ImpedanceVerif: On-Chip Impedance Sensing for System-Level Tampering Detection, T. Mosavirik et al. (2023). Original
26. IBM 4765 Cryptographic Coprocessor Security Module: Security Policy, IBM Corporation (2012). Original
27. PHYSEC SEAL: Change detection for maximum safety, PHYSEC GmbH (2026). Original
28. Tamper-Indicating Enclosures, A Current Survey, H. A. Smartt & Z. N. Gastelum (2015). Original
29. Physical Security and Tamper-Indicating Devices, R. G. Johnston & A. R. E. Garcia (1996). Original
30. Tamper Detection for Safeguards and Treaty Monitoring: Fantasies, Realities, and Potentials, R. G. Johnston (2001). Original
31. Anti-Tamper Radio Meets Reconfigurable Intelligent Surface for System-Level Tamper Detection, M. S. Tabar et al. (2025). Original