Proposal Explorer

Add claims to see which ones the mechanisms address.

Not counted

Excluded by your filters: Bandwidth limits and compartmentalization and Whole-workload recomputation (reproducible packets)

Published attempts to break a system, including those that found failures. Testing history does not show that open flaws are resolved.

Excluded by your filters

• Bandwidth limits and compartmentalization Readiness R1 is below the minimum of R4.
• Whole-workload recomputation (reproducible packets) Readiness R1 is below the minimum of R4.

Family findings

• Bandwidth limits and compartmentalization

  Context for AI 2040 inference-only verification stack. These findings concern the family or other implementations; applicability must be checked against their stated scope.

  • 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. ^{8 9 10}

    Theoretical argument · Significant · Open. On the record

  • 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. ¹⁰

    Theoretical argument · Significant · Open. On the record

  • 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. ¹⁰

    Theoretical argument · Significant · Open. 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. ¹⁰

    Open question · 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. ¹¹

    Theoretical argument · Significant · Open. On the record

Open significant flaws

5 flaws in 2 mechanisms

• 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}

  Theoretical argument · Significant · Open. 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

  Theoretical argument · Significant · Open. On the record

• 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}

  Demonstrated attack · Significant · Open. 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 12}

  Theoretical argument · Significant · Open. On the record

  Related mechanism R1 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 flaw is mitigated. Add

• 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

  Theoretical argument · Significant · Open. On the record

Not yet demonstrated

R1 Bandwidth limits and compartmentalization and R1 Whole-workload recomputation (reproducible packets)

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

• R1 Proofs of useful work for capacity accounting Add

  Excluded by filters: readiness R1

  • Bears on the open significant flaw “Spare compute is outside the scheme” in Whole-workload recomputation (reproducible packets). Proposed as one input to accounting for spare capacity on declared hardware.
• R3 Deterministic and bit-exact inference Add

  Excluded by filters: readiness R3

  • Whole-workload recomputation (reproducible packets) waits on it. Workloads are not reproducible by default, and achieving reproducibility may cost performance.
• R2 Tamper evidence for verifier devices Add

  Excluded by filters: readiness R2

  • Bandwidth limits and compartmentalization 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.
• R1 Memory wiping and proofs of secure erasure Add

  Excluded by filters: readiness R1

  • Bandwidth limits and compartmentalization waits on it. Memory wiping may use existing algorithms, but hardware testing is at an early stage.
• R1 Network taps and certifiers Add

  Excluded by filters: readiness R1

  • Bandwidth limits and compartmentalization waits on it. Passive optical taps work at 400G, but the 800G and 1600G line rates now arriving in data centres are undemonstrated.
  • 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.
• R1 Side-channel suppression for isolated facilities Add

  Excluded by filters: readiness R1

  • Bandwidth limits and compartmentalization waits on it. There is no plan yet for quickly scaling side-channel defences on a frontier cluster; only early theoretical pieces exist.
• R3 Sampled inference recomputation Add

  Excluded by filters: readiness R3

  • Bandwidth limits and compartmentalization depends on it.

Missing prerequisites

• R3 Sampled inference recomputation needed by Bandwidth limits and compartmentalization Add
• R3 Deterministic and bit-exact inference needed by Whole-workload recomputation (reproducible packets) Add
• R1 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 and Whole-workload recomputation (reproducible packets)

Blockers

10 blockers recorded

• Bandwidth limits and compartmentalization
  • 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}
• 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 ⁴
  • 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 4}
  • 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 ¹²

From the family or selected implementation's record. ?

Model weights

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

Unspecified for Bandwidth limits and compartmentalization. Check the implementation record.

Inputs and outputs

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

Unspecified for Bandwidth limits and compartmentalization. Check the implementation record.

Training data

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

Unspecified for Bandwidth limits and compartmentalization. Check the implementation record.

Bandwidth limits and compartmentalization

• R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• R1 RAND secure inference data center (SIDC) design Proposed architecture, RAND

Whole-workload recomputation (reproducible packets)

• R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project

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. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). Original
9. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). Original
10. Traffic Shaping for Workload Classification, Lucid Computing (2026). Original
11. The Tray as a Bandwidth Boundary, Amodo Design (2026). Original
12. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). Original
13. Scaling Recomputation Inference Verification, Amodo Design (2026). Original
14. Proof-of-Learning is Currently More Broken Than You Think, C. Fang et al. (2023). Original