Proposal Explorer

Add claims to see which ones the mechanisms address.

Not counted

Excluded by your filters: Bandwidth limits and compartmentalization and Tamper evidence for verifier devices

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

• Bandwidth limits and compartmentalization: Analysis · excluded by filters

Excluded by your filters

• Bandwidth limits and compartmentalization Needs a verifier device at the prover's site, which the filter rules out.
• Tamper evidence for verifier devices Needs a verifier device at the prover's site, which the filter rules out.

Family findings

• Tamper evidence for verifier devices

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

  • 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. ^{14 15}

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

  • 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. ^{15 16}

    Theoretical argument · 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. ^{17 18 19}

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

Open significant flaws

8 flaws in 2 mechanisms

• 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}

  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. ²

  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. ²

  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. ²

  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. ⁵

  Theoretical argument · Significant · Open. On the record

• 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 8 10}

  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 8 12 13}

  Demonstrated attack · Significant · Open. On the record

Not yet demonstrated

R1 Tamper evidence for verifier devices

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

• R1 Memory wiping and proofs of secure erasure Add
  • Tamper evidence for verifier devices waits on it. Memory wiping may use existing algorithms, but hardware testing is at an early stage.
• R3 Sampled inference recomputation Add
  • Tamper evidence for verifier devices depends on it.
• R1 Network taps and certifiers Add

  Excluded by filters: needs a device on site

  • Bandwidth limits and compartmentalization waits on it. The verifier must know that all traffic leaving a pod crosses the capped, monitored links.
  • Tamper evidence for verifier devices waits on it. Passive optical taps work at 400G, but the 800G and 1600G line rates now arriving in data centres are undemonstrated.
• R1 Side-channel suppression for isolated facilities Add

  Excluded by filters: needs a device on site

  • Tamper evidence for verifier devices waits on it. There is no plan yet for quickly scaling side-channel defences on a frontier cluster; only early theoretical pieces exist.
• R1 Whole-workload recomputation (reproducible packets) Add

  Excluded by filters: needs a device on site

  • Tamper evidence for verifier devices 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

• R3 Sampled inference recomputation needed by Tamper evidence for verifier devices Add
• R1 Whole-workload recomputation (reproducible packets) needed by Tamper evidence for verifier devices Add

Shared foundations

• Network taps and certifiers relied on by Bandwidth limits and compartmentalization and Tamper evidence for verifier devices

Blockers

10 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}
• Tamper evidence for verifier devices
  • 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) ⁸
  • 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 ⁸
  • 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 ^{8 10}
  • 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 ⁸
  • 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 ⁸
  • Robust red-teaming of recomputation schemes has not started, and most algorithm development remains academic. Adversarial validation ^{8 10}

From the family or selected implementation's record. ?

Model weights

Not involved: Bandwidth limits and compartmentalization.

Unspecified for Tamper evidence for verifier devices. Check the implementation record.

Inputs and outputs

Not involved: Bandwidth limits and compartmentalization.

Unspecified for Tamper evidence for verifier devices. Check the implementation record.

Training data

Not involved: Bandwidth limits and compartmentalization.

Unspecified for Tamper evidence for verifier devices. 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

Tamper evidence for verifier devices

• R1 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. Get Involved in Verification, AI Futures Project (2026). Original
9. Verifying international AI deals: Plan A, the state-of-play, and what you can do to help, T. Milton et al. (2026). Original
10. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original
11. Fitting a Network TAP to our Inference Verification Prototype, Amodo Design (2026). Original
12. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
13. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
14. Physical Security and Tamper-Indicating Devices, R. G. Johnston & A. R. E. Garcia (1996). Original
15. Tamper Detection for Safeguards and Treaty Monitoring: Fantasies, Realities, and Potentials, R. G. Johnston (2001). Original
16. Tamper-Indicating Enclosures, A Current Survey, H. A. Smartt & Z. N. Gastelum (2015). Original
17. Secure Physical Enclosures from Covers with Tamper-Resistance, V. Immler et al. (2019). Original
18. Anti-Tamper Radio: System-Level Tamper Detection for Computing Systems, P. Staat et al. (2022). Original
19. Anti-Tamper Radio Meets Reconfigurable Intelligent Surface for System-Level Tamper Detection, M. S. Tabar et al. (2025). Original