# 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-0014&ready=R3 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. - **Minimum readiness: R3 In production.** Keeps mechanisms whose readiness level is at least this one. A level describes the public evidence for a mechanism's stated use, not its cost or feasibility. R3 can still have open critical flaws. 4 of 25 mechanisms on the map pass these filters. ## 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 | | --- | --- | --- | --- | --- | --- | --- | --- | --- | | Bandwidth limits and compartmentalization (excluded by the filters) | R2 | Adversarial | Analysis | Retrofit device | 0 / 5 / 0 | not involved | not involved | not involved | ## Claims No claims chosen. ## Mechanisms ### Bandwidth limits and compartmentalization Capping or removing network links between groups of accelerators, so that serving within each group still works but large training across groups becomes far slower. ([Bandwidth limits and compartmentalization](https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/)) - Assessment: mechanism family. - Readiness: R2 Demonstrated, assessed for monitoring inter-node traffic with operator-run software on four GPUs. - Claims in this proposal: none of them. - Threat model: adversarial prover. Hardware: retrofit device. Prover cooperation: required. Attack testing: analysis. Category: Isolation & system architectures. - What the verifier sees: model weights not involved; inputs and outputs not involved; training data not involved. Caps traffic between groups of chips; it does not read the traffic's content. - Filter conflict: Readiness R2 is below the minimum of R3. ## Properties Not counted as properties, because the filters exclude them: Bandwidth limits and compartmentalization. ## 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** - Bandwidth limits and compartmentalization: Analysis (excluded by filters) ## Limits **Excluded by the filters** - Bandwidth limits and compartmentalization: Readiness R2 is below the minimum of R3. **Open significant flaws** - Low-communication training reduces the bandwidth training needs (theoretical argument, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-1) [2][6][7]. 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. - Operator control of pod routing collapses the bound (theoretical argument, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-2) [2]. 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. - Undeclared local storage raises per-pod capacity (theoretical argument, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-3) [2]. More memory or storage per pod helps an adversary. Lucid requires per-pod storage to be declared, capped and physically inspected. - Training within one pod is not covered (open question, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-4) [2]. 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. - Parallel scale-up switches are hard enforcement points (theoretical argument, in Bandwidth limits and compartmentalization; https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/#flaw-5) [5]. 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. ## 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. - **Tamper evidence for verifier devices** (R2 Demonstrated, assessed for detecting probing of proposed verifier hardware, using server and electronics prototypes as evidence). Excluded by the filters: readiness R2 - Bandwidth limits and compartmentalization waits on it: Shaping devices and routing assignments must be trusted by both parties; Amodo has not yet fully analysed resilience to a compromised DPU. - **Network taps and certifiers** (R1 Proposed, assessed for committing a complete record of cluster traffic, so declared inference can be checked). Excluded by the filters: readiness R1 - Bandwidth limits and compartmentalization waits on it: The verifier must know that all traffic leaving a pod crosses the capped, monitored links. ## Dependencies **Missing prerequisites** - Tamper evidence for verifier devices (R2 Demonstrated, assessed for detecting probing of proposed verifier hardware, using server and electronics prototypes as evidence), needed by Bandwidth limits and compartmentalization **Blockers** - Bandwidth limits and compartmentalization: No cap that a verifier can check has been implemented or red-teamed. (adversarial validation) [2] - Bandwidth limits and compartmentalization: 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] - Bandwidth limits and compartmentalization: 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] - Bandwidth limits and compartmentalization: Advances in low-communication training could shrink the margin that the cap enforces. (capacity bounds) [2][6][7] ## What the verifier sees - Model weights: shown by none; depends on the design for none; hidden by none; not involved in Bandwidth limits and compartmentalization; unspecified for none. - Inputs and outputs: shown by none; depends on the design for none; hidden by none; not involved in Bandwidth limits and compartmentalization; unspecified for none. - Training data: shown by none; depends on the design for none; hidden by none; not involved in Bandwidth limits and compartmentalization; unspecified for none. ## Implementations - Bandwidth limits and compartmentalization: [AI 2040 inference-only verification stack](https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/) (R1, proposed architecture); [RAND secure inference data center (SIDC) design](https://trustbutveri.fyi/implementations/rand-secure-inference-data-centers/) (R1, proposed architecture) ## Sources 1. Verification Plan, R. Dean (2026). https://ai-2040.com/supplements/verification-plan 2. Traffic Shaping for Workload Classification, Lucid Computing (2026). https://lucidcomputing.substack.com/p/traffic-shaping-for-workload-classification 3. 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 4. De-risking Interconnect Limits for AI Verification, A. Scher et al. (2026). https://techgov.intelligence.org/blog/de-risking-interconnect-limits-for-ai-verification 5. The Tray as a Bandwidth Boundary, Amodo Design (2026). https://amododesign.com/notes/2026-03-16-dpu-bandwidth-limiter/ 6. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). https://arxiv.org/abs/2311.08105 7. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). https://arxiv.org/abs/2605.29359