{ "schema_version": "1.3", "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0014,M-0009,M-0019,M-0013", "data_generated": "2026-10-09", "definitions": { "methodology": "https://trustbutveri.fyi/about/methodology/", "readiness": "https://trustbutveri.fyi/about/readiness/", "filters": [ { "id": "prover", "label": "Prover", "question": "How far can the party being checked be trusted?", "options": [ { "value": "cooperative", "label": "Cooperative" }, { "value": "semi-trusted", "label": "Semi-trusted" }, { "value": "adversarial", "label": "Adversarial" } ], "rule": "Keeps mechanisms whose threat model holds against at least this prover. Adversarial is the strongest assumption.", "about": "The prover is the party being checked. Semi-trusted designs rely on part of its stack: usually the chip vendor's hardware root of trust, its firmware or counters, or its supply-chain records. Adversarial designs aim to hold even if it cheats wherever the checks allow, within their stated assumptions." }, { "id": "onsite", "label": "Verifier devices on site", "question": "May the verifier install its own hardware at the prover's sites?", "options": [ { "value": "no", "label": "Not allowed" } ], "rule": "\"Not allowed\" removes mechanisms that need a retrofit device, such as a network tap or a sealed sensor.", "about": "Some mechanisms need a device the verifier owns or trusts at the prover's facility, such as a network tap, a bandwidth limiter or a sealed sensor. Choose Not allowed when the setting rules that out. Inspectors are not covered." }, { "id": "coop", "label": "Prover cooperation", "question": "How much must the prover take part?", "options": [ { "value": "partial", "label": "Partial at most" }, { "value": "none", "label": "Not required" } ], "rule": "\"Partial at most\" removes mechanisms that need the prover's active participation. \"Not required\" keeps only those that work without it.", "about": "Required: the prover takes part, for example by logging requests, producing proofs or opening records. Partial: some access, such as installing a device. Not required: works from outside, such as satellite imagery." }, { "id": "chips", "label": "Chips", "question": "May the proposal depend on new chip designs?", "options": [ { "value": "existing", "label": "Existing chips only" } ], "rule": "\"Existing chips only\" removes mechanisms that need changes to future chip designs.", "about": "New chip features take years to reach a deployed fleet and cover only chips made after they ship. Mechanisms that use shipping features, such as trusted execution environments or performance counters, stay." }, { "id": "ready", "label": "Minimum development status", "question": "Development status", "options": [ { "value": "R1", "label": "Proposed" }, { "value": "R2", "label": "Research demonstration" }, { "value": "R3", "label": "Operational use" }, { "value": "R4", "label": "Legacy independent-evaluation filter", "legacy": true } ], "rule": "Keeps mechanisms whose readiness level is at least this one.", "about": "A level describes the public evidence for a mechanism's stated use, not its cost or feasibility. R3 can still have open critical flaws." }, { "id": "tested", "label": "Attack testing", "question": "How hard has each mechanism been attacked in public?", "options": [ { "value": "analysis", "label": "Published analysis" }, { "value": "red-teamed", "label": "Red-teamed" }, { "value": "independent-red-team", "label": "Independent red-team" } ], "rule": "Keeps mechanisms whose strongest published attack testing is at least this.", "about": "The strongest published attempt to break the mechanism for its verification use: a security analysis, red-teaming by its developers or collaborators, or a red team independent of them." }, { "id": "hide", "label": "Keep hidden from the verifier", "question": "What must the verifier never see?", "options": [ { "value": "weights", "label": "Model weights" }, { "value": "io", "label": "Inputs and outputs" }, { "value": "training", "label": "Training data" } ], "rule": "Removes mechanisms that show the asset to the verifier. Conditional or unspecified exposure stays with a note and needs checking against the privacy requirement.", "about": "Model weights: the checked model's parameters. Inputs and outputs: the requests a deployed model serves and its responses. Training data: what a model was trained on. Each mechanism's exposure is the editors' reading of its record: shown, depends on the design (kept, with a note), hidden, not involved, or unspecified for a selected implementation. Code and configuration are not covered yet." } ], "exposure": "For model weights, inputs and outputs, and training data. This is the editors' reading of each mechanism's record (its threat model, how it works and its limitations), not a field of the record. Shown: the verifier sees it. Depends: on the design or variant, or the verifier sees only samples. Hidden: the verifier sees only commitments, hashes, proofs or results. Not involved: the record does not handle it. Unspecified: the selected implementation has no asset-specific assessment here.", "claim_status": { "addressed": "A mechanism in the proposal is aimed at this claim and is not excluded by the filters.", "partly-addressed": "Only supporting mechanisms, or mechanisms aimed at it that the filters exclude.", "unaddressed": "No mechanism in the proposal addresses this claim." }, "finding_classification": { "failure": { "label": "Known failures", "singular": "Known failure", "anchor": "known-flaws" }, "scope-limitation": { "label": "Scope limitations", "singular": "Scope limitation", "anchor": "scope-limitations" }, "open-question": { "label": "Open questions", "singular": "Open question", "anchor": "open-questions" } }, "finding_scope": "Evidence scope describes where a finding was demonstrated; it does not establish applicability to every implementation in the mechanism family.", "claim_finding_scope": "open_critical_findings names active failures on the assessed records; open_critical_context names conditional family failures whose implementation applicability is unassessed.", "legacy_status": "The status field retains covered/partial/none for compatibility. It names claim links, never successful verification. Use claim_status and status_label for presentation." }, "filters": { "prover": "", "onsite": "", "coop": "", "chips": "", "ready": "", "tested": "", "hide": [] }, "mechanisms_passing_filters": 25, "claims": [], "mechanisms": [ { "id": "M-0014", "title": "Bandwidth limits and compartmentalization", "url": "https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/", "assessment_record": { "id": "M-0014", "title": "Bandwidth limits and compartmentalization", "url": "https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/" }, "finding_counts": { "failure": 2, "scope_limitation": 2, "open_question": 1, "open_failures": { "critical": 0, "significant": 2, "minor": 0 } }, "selected_implementation": null, "readiness": { "level": "R2", "scope": "monitoring inter-node traffic with operator-run software on four GPUs", "confidence": "low", "evidence": [ "S-0067", "S-1301", "S-0018", "S-3220", "S-1313" ] }, "development_status": { "code": "R2", "label": "Research demonstration", "short": "Research demo", "rank": 2, "legacy_code": "R2" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 2, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1301" ] }, { "n": 5, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1313" ] } ], "open_failures": { "critical": 0, "significant": 2, "minor": 0 } }, "assessed_properties": { "threat_model": "adversarial", "hardware_requirement": "retrofit-device", "prover_cooperation": "required", "adversarial_evaluation": "analysis" }, "claims": [], "exposure": { "weights": "none", "io": "none", "training": "none", "note": "Caps traffic between groups of chips; it does not read the traffic's content." }, "family_finding_context": [], "filter_issues": [] }, { "id": "M-0009", "title": "Hardware-enabled guarantees (flexHEG) and guarantee processors", "url": "https://trustbutveri.fyi/mechanisms/flexheg-guarantee-processors/", "assessment_record": { "id": "M-0009", "title": "Hardware-enabled guarantees (flexHEG) and guarantee processors", "url": "https://trustbutveri.fyi/mechanisms/flexheg-guarantee-processors/" }, "finding_counts": { "failure": 3, "scope_limitation": 2, "open_question": 1, "open_failures": { "critical": 0, "significant": 3, "minor": 0 } }, "selected_implementation": null, "readiness": { "level": "R1", "scope": "checking and enforcing training-compute limits on chips, against adversaries up to states", "confidence": "medium", "evidence": [ "S-0035", "S-1204", "S-1205", "S-0057", "S-0056", "S-0006" ] }, "development_status": { "code": "R1", "label": "Proposed", "short": "Proposed", "rank": 1, "legacy_code": "R1" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 1, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1204", "S-0057" ] }, { "n": 2, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1204" ] }, { "n": 4, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1204" ] } ], "open_failures": { "critical": 0, "significant": 3, "minor": 0 } }, "assessed_properties": { "threat_model": "adversarial", "hardware_requirement": "new-chip", "prover_cooperation": "required", "adversarial_evaluation": "analysis" }, "claims": [], "exposure": { "weights": "hidden", "io": "hidden", "training": "hidden", "note": "The guarantee processor sees the chip's traffic inside a sealed enclosure and reports only whether rules were kept." }, "family_finding_context": [], "filter_issues": [] }, { "id": "M-0019", "title": "Chip registries and manufacturing records", "url": "https://trustbutveri.fyi/mechanisms/chip-registries-and-manufacturing-records/", "assessment_record": { "id": "M-0019", "title": "Chip registries and manufacturing records", "url": "https://trustbutveri.fyi/mechanisms/chip-registries-and-manufacturing-records/" }, "finding_counts": { "failure": 1, "scope_limitation": 2, "open_question": 0, "open_failures": { "critical": 0, "significant": 1, "minor": 0 } }, "selected_implementation": null, "readiness": { "level": "R1", "scope": "a checkable record of which chips were made and who declared owning them", "confidence": "medium", "evidence": [ "S-0002", "S-1402", "S-1408", "S-0007" ] }, "development_status": { "code": "R1", "label": "Proposed", "short": "Proposed", "rank": 1, "legacy_code": "R1" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 2, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1402" ] } ], "open_failures": { "critical": 0, "significant": 1, "minor": 0 } }, "assessed_properties": { "threat_model": "semi-trusted", "hardware_requirement": "existing-features", "prover_cooperation": "required", "adversarial_evaluation": "analysis" }, "claims": [], "exposure": { "weights": "none", "io": "none", "training": "none", "note": "Records chip identities and owners; it does not handle model data." }, "family_finding_context": [], "filter_issues": [] }, { "id": "M-0013", "title": "Network taps and certifiers", "url": "https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/", "assessment_record": { "id": "M-0013", "title": "Network taps and certifiers", "url": "https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/" }, "finding_counts": { "failure": 3, "scope_limitation": 3, "open_question": 0, "open_failures": { "critical": 0, "significant": 2, "minor": 0 } }, "selected_implementation": null, "readiness": { "level": "R1", "scope": "committing a complete record of cluster traffic, so declared inference can be checked", "confidence": "medium", "evidence": [ "S-1300", "S-0031", "S-0018", "S-0067", "S-1312", "S-1007", "S-1319", "S-1320" ] }, "development_status": { "code": "R1", "label": "Proposed", "short": "Proposed", "rank": 1, "legacy_code": "R1" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 1, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1300", "S-1507" ] }, { "n": 4, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1312" ] }, { "n": 6, "severity": "minor", "status": "mitigated", "evidence_scope": "unassessed", "sources": [ "S-1300" ] } ], "open_failures": { "critical": 0, "significant": 2, "minor": 0 } }, "assessed_properties": { "threat_model": "adversarial", "hardware_requirement": "retrofit-device", "prover_cooperation": "required", "adversarial_evaluation": "analysis" }, "claims": [], "exposure": { "weights": "partial", "io": "partial", "training": "partial", "note": "Only hashes leave the site; records picked for a challenge are opened for replay at a verification facility." }, "family_finding_context": [], "filter_issues": [] } ], "strengths": { "covered": [], "production": [], "operationalUse": [], "adversarial": [ "M-0014", "M-0009", "M-0013" ], "noNewHardware": [ "M-0019" ], "mitigated": [ { "mech": "M-0013", "n": 6, "historical": false, "title": "Verifier dictionary attacks on hashes", "classification": "failure", "kind": "theoretical-argument", "severity": "minor", "status": "mitigated", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Hashes of very short outputs could be brute-forced by the verifier. The paper recommends hashing at least 5 tokens together, or at least 10 if the attacker filters for likely tokens.", "response": null, "sources": [ "S-1300" ] } ], "notCounted": [] }, "properties": { "covered": [], "production": [], "operationalUse": [], "adversarial": [ "M-0014", "M-0009", "M-0013" ], "noNewHardware": [ "M-0019" ], "mitigated": [ { "mech": "M-0013", "n": 6, "historical": false, "title": "Verifier dictionary attacks on hashes", "classification": "failure", "kind": "theoretical-argument", "severity": "minor", "status": "mitigated", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Hashes of very short outputs could be brute-forced by the verifier. The paper recommends hashing at least 5 tokens together, or at least 10 if the attacker filters for likely tokens.", "response": null, "sources": [ "S-1300" ] } ], "notCounted": [] }, "attack_testing": [ { "id": "M-0014", "record": "M-0014", "evaluation": "analysis", "in_setting": true }, { "id": "M-0009", "record": "M-0009", "evaluation": "analysis", "in_setting": true }, { "id": "M-0019", "record": "M-0019", "evaluation": "analysis", "in_setting": true }, { "id": "M-0013", "record": "M-0013", "evaluation": "analysis", "in_setting": true } ], "selected_implementations": {}, "weaknesses": { "gaps": [], "excluded": [], "unlinked": [], "critical": [], "significant": [ { "mech": "M-0014", "n": 2, "historical": false, "title": "Operator control of pod routing collapses the bound", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "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.", "response": null, "sources": [ "S-1301" ] }, { "mech": "M-0014", "n": 5, "historical": false, "title": "Parallel scale-up switches are hard enforcement points", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "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.", "response": null, "sources": [ "S-1313" ] }, { "mech": "M-0009", "n": 1, "historical": false, "title": "State attackers can likely defeat current secure enclosures", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "The flexHEG authors write that \"nation-state attackers can likely compromise the best current secure enclosures\", and that the marginal cost of circumvention per device is hard to estimate. RAND similarly judges that anti-tamper measures \"would not be insurmountable for a determined and well-resourced adversary\", although they raise costs and can reveal tampering.", "response": null, "sources": [ "S-1204", "S-0057" ] }, { "mech": "M-0009", "n": 2, "historical": false, "title": "Firmware-only retrofits rely on Secure Boot, which fault injection can bypass", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Part II notes that the most common attack on Secure Boot replaces the firmware and applies a voltage glitch while the signature is being checked. It also notes that sophisticated actors may use microprobing or laser voltage probing to read key registers.", "response": null, "sources": [ "S-1204" ] }, { "mech": "M-0009", "n": 4, "historical": false, "title": "FLOP accounting can be laundered through external data", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Results of earlier or parallel workloads could be hidden in the \"external data\" fed to a device, which would falsify the total FLOP count unless the inputs are explained or time delays are imposed.", "response": null, "sources": [ "S-1204" ] }, { "mech": "M-0019", "n": 2, "historical": false, "title": "Documents and serial numbers can be forged", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Avellar and Grunewald note that export documents can be forged, that companies can hide information behind obscure corporate structures, and that it may be possible to forge serial numbers on chips and racks. They recommend cryptographic attestation of a powered-on chip as an extra check.", "response": null, "sources": [ "S-1402" ] }, { "mech": "M-0013", "n": 1, "historical": false, "title": "Output nondeterminism leaves covert capacity", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Hashing cannot remove information hidden in the outputs themselves. The Secure Gateway Device paper estimates that about 0.1 bit per token remains even with seed-synchronized replay checks. For a 200k-GPU inference cluster at full load (2,000 tokens per GPU per second), that is about 40 Mbit/s of covert egress, enough to move a 1 TB model in under three days. The paper names this the core remaining challenge and points to deterministic replay or active scrubbing of hardware-induced entropy. An independent study found that an adversary who chooses the prompts roughly doubles the bits leaked per token under Gumbel-based inference verification; see Bounding unexplained information in outputs.", "response": null, "sources": [ "S-1300", "S-1507" ], "helps": [ { "by": "M-0002", "how": "Deterministic replay is one of the two remedies the flaw's source names." }, { "by": "M-0024", "how": "Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict." } ] }, { "mech": "M-0013", "n": 4, "historical": false, "title": "Residual side channels in simple passive setups", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Amodo's analysis of its own tapped prototype lists unvalidated header fields, timing of permitted traffic and variation in response formatting as residual channels, and concludes that the passive tap must be replaced by an active one.", "response": null, "sources": [ "S-1312" ] } ], "criticalMechanisms": [], "significantMechanisms": [ "M-0014", "M-0009", "M-0019", "M-0013" ], "familyContext": [], "scopeLimitations": [ { "mech": "M-0014", "n": 3, "historical": false, "title": "Undeclared local storage raises per-pod capacity", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "More memory or storage per pod helps an adversary. Lucid requires per-pod storage to be declared, capped and physically inspected.", "response": null, "sources": [ "S-1301" ] }, { "mech": "M-0014", "n": 4, "historical": false, "title": "Training within one pod is not covered", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "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.", "response": null, "sources": [ "S-1301" ] }, { "mech": "M-0009", "n": 3, "historical": false, "title": "Many important rules cannot be checked on-chip", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Malicious intent \"is not a technical property observable on-chip\", and misuse depends on what is done with a computation's results. A guarantee processor cannot easily tell whether a network is the whole system or one expert in a mixture-of-experts system. Part III judges that a fully local ruleset \"may not be entirely feasible\" for the same reason.", "response": null, "sources": [ "S-0035", "S-1205" ] }, { "mech": "M-0009", "n": 6, "historical": false, "title": "Coverage stops at flexHEG-equipped chips", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Motivated actors will always be able to use some compute that is not flexHEG-equipped. Recalling existing consumer GPUs would likely be impractical, and reaching perfect coverage, or conclusively proving that no secret government data centres exist, would be \"practically quite difficult\".", "response": null, "sources": [ "S-0035", "S-1205" ], "helps": [ { "by": "M-0019", "how": "Accounts for which chips exist and who holds them." }, { "by": "M-0020", "how": "Looks for undeclared facilities that hold other chips." } ] }, { "mech": "M-0019", "n": 1, "historical": false, "title": "Records cover only chips that were recorded", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "A registry or commitment accounts only for chips entered into it. Cankaya asks how a verifier would know it had found all chips, or how much \"dark compute\" remains, and notes that a fraudulent original record would mean unregistered chips had been made in advance. Halstead and Larsen propose reconstructing earlier production by auditing upstream suppliers.", "response": null, "sources": [ "S-1408", "S-1410" ], "helps": [ { "by": "M-0020", "how": "Looks for large data centres that were never declared, which a registry cannot show." } ] }, { "mech": "M-0019", "n": 3, "historical": false, "title": "Insiders could alter records before they are fixed", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Cankaya argues that insiders who can photograph process secrets could also tamper with production records. A commitment makes changes after publication detectable, but it cannot show that the records were accurate when committed.", "response": null, "sources": [ "S-1408" ] }, { "mech": "M-0013", "n": 2, "historical": false, "title": "Some links cannot be passively tapped", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Cankaya notes that copper-connected scale-up domains (for example NVL72 racks and TPU v7 cubes) are much harder to tap than fibre, and that optical budgets make passive taps impractical on 400GBASE-SR8 multimode links. Amodo found no taps advertised for 53 GBaud links as of May 2026.", "response": null, "sources": [ "S-0031", "S-1310" ] }, { "mech": "M-0013", "n": 3, "historical": false, "title": "Encrypted fabrics hide plaintext from both parties", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Cankaya notes that with TEE-protected sessions whose keys are ephemeral and managed inside the TEE, neither the operator nor the manufacturer can recover session keys after the session, so tapped traffic could not be opened for recomputation. For other encrypted fabrics, the operator can retain keys.", "response": null, "sources": [ "S-0031" ] }, { "mech": "M-0013", "n": 5, "historical": false, "title": "Completeness rests on physical monitoring left out of scope", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "The Secure Gateway Device paper assumes the facility is physically monitored, and states that the whole architecture depends on the device being the only communication channel. It names radio emanation, power-line signalling and thermal channels as covert channels beyond that scope.", "response": null, "sources": [ "S-1300" ], "helps": [ { "by": "M-0022", "how": "Addresses the radio, power-line and thermal channels that network-level designs leave out." } ] } ], "openQuestions": [ { "mech": "M-0014", "n": 1, "historical": false, "title": "Low-communication training reduces the bandwidth training needs", "classification": "open-question", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "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.", "response": null, "sources": [ "S-1314", "S-0060", "S-1301" ] }, { "mech": "M-0009", "n": 5, "historical": false, "title": "Supply-chain diversion and hidden backdoors", "classification": "open-question", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Components could be diverted before a guarantee processor is added, and backdoors could be introduced during design or manufacturing. Open-source designs and physical scans of randomly selected chips are proposed as countermeasures. Part III proposes international oversight of production and extensive testing of a random sample of finished devices.", "response": null, "sources": [ "S-1204", "S-1205" ], "helps": [ { "by": "M-0019", "how": "Records each chip's identity and owner from the fab onwards, which bears on diversion before a guarantee processor is fitted. It does not address hidden backdoors." } ] } ], "minor": 0, "minorFindings": [], "minorBy": [], "notDemonstrated": [ "M-0009", "M-0019", "M-0013" ], "newChip": [ "M-0009" ] }, "findings": [ { "mech": "M-0014", "record": "M-0014", "n": 1, "historical": false, "title": "Low-communication training reduces the bandwidth training needs", "classification": "open-question", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "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.", "response": null, "sources": [ "S-1314", "S-0060", "S-1301" ] }, { "mech": "M-0014", "record": "M-0014", "n": 2, "historical": false, "title": "Operator control of pod routing collapses the bound", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "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.", "response": null, "sources": [ "S-1301" ] }, { "mech": "M-0014", "record": "M-0014", "n": 3, "historical": false, "title": "Undeclared local storage raises per-pod capacity", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "More memory or storage per pod helps an adversary. Lucid requires per-pod storage to be declared, capped and physically inspected.", "response": null, "sources": [ "S-1301" ] }, { "mech": "M-0014", "record": "M-0014", "n": 4, "historical": false, "title": "Training within one pod is not covered", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "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.", "response": null, "sources": [ "S-1301" ] }, { "mech": "M-0014", "record": "M-0014", "n": 5, "historical": false, "title": "Parallel scale-up switches are hard enforcement points", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "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.", "response": null, "sources": [ "S-1313" ] }, { "mech": "M-0009", "record": "M-0009", "n": 1, "historical": false, "title": "State attackers can likely defeat current secure enclosures", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "The flexHEG authors write that \"nation-state attackers can likely compromise the best current secure enclosures\", and that the marginal cost of circumvention per device is hard to estimate. RAND similarly judges that anti-tamper measures \"would not be insurmountable for a determined and well-resourced adversary\", although they raise costs and can reveal tampering.", "response": null, "sources": [ "S-1204", "S-0057" ] }, { "mech": "M-0009", "record": "M-0009", "n": 2, "historical": false, "title": "Firmware-only retrofits rely on Secure Boot, which fault injection can bypass", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Part II notes that the most common attack on Secure Boot replaces the firmware and applies a voltage glitch while the signature is being checked. It also notes that sophisticated actors may use microprobing or laser voltage probing to read key registers.", "response": null, "sources": [ "S-1204" ] }, { "mech": "M-0009", "record": "M-0009", "n": 3, "historical": false, "title": "Many important rules cannot be checked on-chip", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Malicious intent \"is not a technical property observable on-chip\", and misuse depends on what is done with a computation's results. A guarantee processor cannot easily tell whether a network is the whole system or one expert in a mixture-of-experts system. Part III judges that a fully local ruleset \"may not be entirely feasible\" for the same reason.", "response": null, "sources": [ "S-0035", "S-1205" ] }, { "mech": "M-0009", "record": "M-0009", "n": 4, "historical": false, "title": "FLOP accounting can be laundered through external data", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Results of earlier or parallel workloads could be hidden in the \"external data\" fed to a device, which would falsify the total FLOP count unless the inputs are explained or time delays are imposed.", "response": null, "sources": [ "S-1204" ] }, { "mech": "M-0009", "record": "M-0009", "n": 5, "historical": false, "title": "Supply-chain diversion and hidden backdoors", "classification": "open-question", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Components could be diverted before a guarantee processor is added, and backdoors could be introduced during design or manufacturing. Open-source designs and physical scans of randomly selected chips are proposed as countermeasures. Part III proposes international oversight of production and extensive testing of a random sample of finished devices.", "response": null, "sources": [ "S-1204", "S-1205" ], "helps": [ { "by": "M-0019", "how": "Records each chip's identity and owner from the fab onwards, which bears on diversion before a guarantee processor is fitted. It does not address hidden backdoors." } ] }, { "mech": "M-0009", "record": "M-0009", "n": 6, "historical": false, "title": "Coverage stops at flexHEG-equipped chips", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Motivated actors will always be able to use some compute that is not flexHEG-equipped. Recalling existing consumer GPUs would likely be impractical, and reaching perfect coverage, or conclusively proving that no secret government data centres exist, would be \"practically quite difficult\".", "response": null, "sources": [ "S-0035", "S-1205" ], "helps": [ { "by": "M-0019", "how": "Accounts for which chips exist and who holds them." }, { "by": "M-0020", "how": "Looks for undeclared facilities that hold other chips." } ] }, { "mech": "M-0019", "record": "M-0019", "n": 1, "historical": false, "title": "Records cover only chips that were recorded", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "A registry or commitment accounts only for chips entered into it. Cankaya asks how a verifier would know it had found all chips, or how much \"dark compute\" remains, and notes that a fraudulent original record would mean unregistered chips had been made in advance. Halstead and Larsen propose reconstructing earlier production by auditing upstream suppliers.", "response": null, "sources": [ "S-1408", "S-1410" ], "helps": [ { "by": "M-0020", "how": "Looks for large data centres that were never declared, which a registry cannot show." } ] }, { "mech": "M-0019", "record": "M-0019", "n": 2, "historical": false, "title": "Documents and serial numbers can be forged", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Avellar and Grunewald note that export documents can be forged, that companies can hide information behind obscure corporate structures, and that it may be possible to forge serial numbers on chips and racks. They recommend cryptographic attestation of a powered-on chip as an extra check.", "response": null, "sources": [ "S-1402" ] }, { "mech": "M-0019", "record": "M-0019", "n": 3, "historical": false, "title": "Insiders could alter records before they are fixed", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Cankaya argues that insiders who can photograph process secrets could also tamper with production records. A commitment makes changes after publication detectable, but it cannot show that the records were accurate when committed.", "response": null, "sources": [ "S-1408" ] }, { "mech": "M-0013", "record": "M-0013", "n": 1, "historical": false, "title": "Output nondeterminism leaves covert capacity", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Hashing cannot remove information hidden in the outputs themselves. The Secure Gateway Device paper estimates that about 0.1 bit per token remains even with seed-synchronized replay checks. For a 200k-GPU inference cluster at full load (2,000 tokens per GPU per second), that is about 40 Mbit/s of covert egress, enough to move a 1 TB model in under three days. The paper names this the core remaining challenge and points to deterministic replay or active scrubbing of hardware-induced entropy. An independent study found that an adversary who chooses the prompts roughly doubles the bits leaked per token under Gumbel-based inference verification; see Bounding unexplained information in outputs.", "response": null, "sources": [ "S-1300", "S-1507" ], "helps": [ { "by": "M-0002", "how": "Deterministic replay is one of the two remedies the flaw's source names." }, { "by": "M-0024", "how": "Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict." } ] }, { "mech": "M-0013", "record": "M-0013", "n": 2, "historical": false, "title": "Some links cannot be passively tapped", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Cankaya notes that copper-connected scale-up domains (for example NVL72 racks and TPU v7 cubes) are much harder to tap than fibre, and that optical budgets make passive taps impractical on 400GBASE-SR8 multimode links. Amodo found no taps advertised for 53 GBaud links as of May 2026.", "response": null, "sources": [ "S-0031", "S-1310" ] }, { "mech": "M-0013", "record": "M-0013", "n": 3, "historical": false, "title": "Encrypted fabrics hide plaintext from both parties", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Cankaya notes that with TEE-protected sessions whose keys are ephemeral and managed inside the TEE, neither the operator nor the manufacturer can recover session keys after the session, so tapped traffic could not be opened for recomputation. For other encrypted fabrics, the operator can retain keys.", "response": null, "sources": [ "S-0031" ] }, { "mech": "M-0013", "record": "M-0013", "n": 4, "historical": false, "title": "Residual side channels in simple passive setups", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Amodo's analysis of its own tapped prototype lists unvalidated header fields, timing of permitted traffic and variation in response formatting as residual channels, and concludes that the passive tap must be replaced by an active one.", "response": null, "sources": [ "S-1312" ] }, { "mech": "M-0013", "record": "M-0013", "n": 5, "historical": false, "title": "Completeness rests on physical monitoring left out of scope", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "The Secure Gateway Device paper assumes the facility is physically monitored, and states that the whole architecture depends on the device being the only communication channel. It names radio emanation, power-line signalling and thermal channels as covert channels beyond that scope.", "response": null, "sources": [ "S-1300" ], "helps": [ { "by": "M-0022", "how": "Addresses the radio, power-line and thermal channels that network-level designs leave out." } ] }, { "mech": "M-0013", "record": "M-0013", "n": 6, "historical": false, "title": "Verifier dictionary attacks on hashes", "classification": "failure", "kind": "theoretical-argument", "severity": "minor", "status": "mitigated", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Hashes of very short outputs could be brute-forced by the verifier. The paper recommends hashing at least 5 tokens together, or at least 10 if the attacker filters for likely tokens.", "response": null, "sources": [ "S-1300" ] } ], "possible_additions": [ { "id": "M-0002", "title": "Deterministic and bit-exact inference", "url": "https://trustbutveri.fyi/mechanisms/deterministic-inference/", "readiness": "R3", "development_status": { "code": "R3", "label": "Operational use", "short": "Operational use", "rank": 3, "legacy_code": "R3" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [], "open_failures": { "critical": 0, "significant": 0, "minor": 0 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "flaw", "mech": "M-0013", "n": 1, "title": "Output nondeterminism leaves covert capacity", "severity": "significant", "how": "Deterministic replay is one of the two remedies the flaw's source names." }, { "kind": "blocker", "mech": "M-0013", "text": "Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove." } ] }, { "id": "M-0024", "title": "Bounding unexplained information in outputs", "url": "https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/", "readiness": "R2", "development_status": { "code": "R2", "label": "Research demonstration", "short": "Research demo", "rank": 2, "legacy_code": "R2" }, "security_evidence": { "attack_testing": { "status": "independent-red-team", "label": "Published attack testing", "kind": "practical", "attribution": "Independent team" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 1, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1507", "S-0015" ] } ], "open_failures": { "critical": 0, "significant": 1, "minor": 0 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "flaw", "mech": "M-0013", "n": 1, "title": "Output nondeterminism leaves covert capacity", "severity": "significant", "how": "Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict." } ] }, { "id": "M-0017", "title": "Tamper evidence for verifier devices", "url": "https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/", "readiness": "R2", "development_status": { "code": "R2", "label": "Research demonstration", "short": "Research demo", "rank": 2, "legacy_code": "R2" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 1, "severity": "significant", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-1317", "S-1318" ] }, { "n": 3, "severity": "significant", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-1315", "S-0052", "S-3261" ] } ], "open_failures": { "critical": 0, "significant": 2, "minor": 0 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "blocker", "mech": "M-0014", "text": "Shaping devices and routing assignments must be trusted by both parties; Amodo has not yet fully analysed resilience to a compromised DPU." }, { "kind": "blocker", "mech": "M-0009", "text": "State-level attackers who hold the hardware can likely compromise the best current secure enclosures." }, { "kind": "blocker", "mech": "M-0013", "text": "Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them." } ] }, { "id": "M-0022", "title": "Side-channel suppression for isolated facilities", "url": "https://trustbutveri.fyi/mechanisms/side-channel-suppression/", "readiness": "R1", "development_status": { "code": "R1", "label": "Proposed", "short": "Proposed", "rank": 1, "legacy_code": "R1" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [], "open_failures": { "critical": 0, "significant": 0, "minor": 0 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "blocker", "mech": "M-0013", "text": "Radio, power-line and thermal channels are not addressed by network-level designs." } ] }, { "id": "M-0001", "title": "Sampled inference recomputation", "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/", "readiness": "R3", "development_status": { "code": "R3", "label": "Operational use", "short": "Operational use", "rank": 3, "legacy_code": "R3" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 1, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-0020", "S-0015", "S-1507" ] }, { "n": 3, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1000", "S-0016" ] }, { "n": 4, "severity": "minor", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-0016" ] } ], "open_failures": { "critical": 0, "significant": 2, "minor": 1 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "prerequisite", "mech": "M-0013" } ] }, { "id": "M-0008", "title": "TEE remote attestation for AI workloads", "url": "https://trustbutveri.fyi/mechanisms/tee-remote-attestation/", "readiness": "R3", "development_status": { "code": "R3", "label": "Operational use", "short": "Operational use", "rank": 3, "legacy_code": "R3" }, "security_evidence": { "attack_testing": { "status": "independent-red-team", "label": "Published attack testing", "kind": "practical", "attribution": "Independent team" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 1, "severity": "critical", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-1202", "S-3126", "S-0012", "S-1206", "S-0014", "S-1210", "S-1212", "S-3127" ] }, { "n": 2, "severity": "critical", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-1210", "S-1211" ] }, { "n": 3, "severity": "critical", "status": "mitigated", "evidence_scope": "mechanism", "sources": [ "S-1212", "S-1213", "S-3127", "S-3128" ] }, { "n": 4, "severity": "significant", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-1202" ] }, { "n": 5, "severity": "significant", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-0012", "S-0009", "S-0014", "S-3123", "S-3129" ] }, { "n": 8, "severity": "significant", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-0014", "S-0009", "S-3130", "S-3131" ] } ], "open_failures": { "critical": 2, "significant": 3, "minor": 0 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "prerequisite", "mech": "M-0009" } ] } ], "goal": null, "design": null, "dependencies": { "prerequisites": [ { "id": "M-0017", "neededBy": [ "M-0014", "M-0013" ] }, { "id": "M-0008", "neededBy": [ "M-0009" ] }, { "id": "M-0001", "neededBy": [ "M-0013" ] }, { "id": "M-0002", "neededBy": [ "M-0013" ] }, { "id": "M-0022", "neededBy": [ "M-0013" ] } ], "shared": [ { "id": "M-0017", "by": [ "M-0014", "M-0009", "M-0013" ], "inProposal": false } ], "blockers": [ { "mech": "M-0014", "n": 1, "historical": false, "text": "No cap that a verifier can check has been implemented or red-teamed.", "theme": "adversarial-validation", "blocked_by": null, "sources": [ "S-1301" ], "inProposal": null }, { "mech": "M-0014", "n": 2, "historical": false, "text": "The verifier must know that all traffic leaving a pod crosses the capped, monitored links.", "theme": "coverage-hidden-compute", "blocked_by": "M-0013", "sources": [ "S-0018" ], "inProposal": true }, { "mech": "M-0014", "n": 3, "historical": false, "text": "Shaping devices and routing assignments must be trusted by both parties; Amodo has not yet fully analysed resilience to a compromised DPU.", "theme": "hardware-trust", "blocked_by": "M-0017", "sources": [ "S-1301", "S-1313" ], "inProposal": false }, { "mech": "M-0014", "n": 4, "historical": false, "text": "Advances in low-communication training could shrink the margin that the cap enforces.", "theme": "capacity-bounds", "blocked_by": null, "sources": [ "S-1314", "S-0060", "S-1301" ], "inProposal": null }, { "mech": "M-0009", "n": 1, "historical": false, "text": "Integrated flexHEG needs substantial help from the accelerator manufacturer, and the authors estimate 3.7–7.9 years, from when the manufacturer starts work, for such hardware to displace other accelerators in frontier development.", "theme": "access-governance", "blocked_by": null, "sources": [ "S-1204" ], "inProposal": null }, { "mech": "M-0009", "n": 2, "historical": false, "text": "State-level attackers who hold the hardware can likely compromise the best current secure enclosures.", "theme": "hardware-trust", "blocked_by": "M-0017", "sources": [ "S-1204", "S-0057" ], "inProposal": false }, { "mech": "M-0009", "n": 3, "historical": false, "text": "Rival states would need to trust the design and manufacture of guarantee processors and enclosures, for example through open design, redundant processors from each side or oversight of production.", "theme": "hardware-trust", "blocked_by": null, "sources": [ "S-1205", "S-0035" ], "inProposal": null }, { "mech": "M-0009", "n": 4, "historical": false, "text": "Restricting future rule updates would need a formal language for rules, which the authors judge most likely infeasible for early flexHEG versions.", "theme": "protocol-soundness", "blocked_by": null, "sources": [ "S-0035" ], "inProposal": null }, { "mech": "M-0009", "n": 5, "historical": false, "text": "Governing all relevant chips depends on knowing where they are, through chip registries and detection of undeclared facilities.", "theme": "coverage-hidden-compute", "blocked_by": "M-0019", "sources": [ "S-1205" ], "inProposal": true }, { "mech": "M-0019", "n": 1, "historical": false, "text": "No implementation of an AI chip registry has been publicly reported, and covering re-exports would need cooperation from re-exporters and foreign governments that may not be feasible everywhere.", "theme": "access-governance", "blocked_by": null, "sources": [ "S-1402", "S-0002" ], "inProposal": null }, { "mech": "M-0019", "n": 2, "historical": false, "text": "Linking records to physical chips needs hard-to-spoof unique IDs and inspections.", "theme": "hardware-trust", "blocked_by": null, "sources": [ "S-0002", "S-1402", "S-1408" ], "inProposal": null }, { "mech": "M-0019", "n": 3, "historical": false, "text": "Chips produced before a registry starts must be reconstructed from supplier records.", "theme": "coverage-hidden-compute", "blocked_by": null, "sources": [ "S-1408", "S-1410" ], "inProposal": null }, { "mech": "M-0013", "n": 1, "historical": false, "text": "No complete verification tap has been demonstrated at production frontend link rates, and on the tested CPU no hash algorithm reached line rate with minimum-size frames.", "theme": "performance-compatibility", "blocked_by": null, "sources": [ "S-1311", "S-1310" ], "inProposal": null }, { "mech": "M-0013", "n": 2, "historical": false, "text": "Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove.", "theme": "evidence-binding", "blocked_by": "M-0002", "sources": [ "S-1300" ], "inProposal": false }, { "mech": "M-0013", "n": 3, "historical": false, "text": "Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them.", "theme": "hardware-trust", "blocked_by": "M-0017", "sources": [ "S-1300", "S-0018" ], "inProposal": false }, { "mech": "M-0013", "n": 4, "historical": false, "text": "Radio, power-line and thermal channels are not addressed by network-level designs.", "theme": "coverage-hidden-compute", "blocked_by": "M-0022", "sources": [ "S-1300" ], "inProposal": false }, { "mech": "M-0013", "n": 5, "historical": false, "text": "Red-teaming by specialists is called for but has not been reported.", "theme": "adversarial-validation", "blocked_by": null, "sources": [ "S-1300" ], "inProposal": null } ] }, "exposure": { "weights": { "shown": [], "partial": [ "M-0013" ], "hidden": [ "M-0009" ], "none": [ "M-0014", "M-0019" ], "unknown": [] }, "io": { "shown": [], "partial": [ "M-0013" ], "hidden": [ "M-0009" ], "none": [ "M-0014", "M-0019" ], "unknown": [] }, "training": { "shown": [], "partial": [ "M-0013" ], "hidden": [ "M-0009" ], "none": [ "M-0014", "M-0019" ], "unknown": [] } }, "implementations": [ { "mechanism": "M-0014", "selected": null, "implementations": [ { "id": "I-0011", "title": "AI 2040 inference-only verification stack", "url": "https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/" }, { "id": "I-0010", "title": "RAND secure inference data center (SIDC) design", "url": "https://trustbutveri.fyi/implementations/rand-secure-inference-data-centers/" } ] }, { "mechanism": "M-0009", "selected": null, "implementations": [] }, { "mechanism": "M-0019", "selected": null, "implementations": [] }, { "mechanism": "M-0013", "selected": null, "implementations": [ { "id": "I-0011", "title": "AI 2040 inference-only verification stack", "url": "https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/" }, { "id": "I-0012", "title": "Low-trust AI compute verification system overview", "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/" }, { "id": "I-0008", "title": "SASH confidential network logger", "url": "https://trustbutveri.fyi/implementations/sash-confidential-network-logger/" } ] } ], "sources": [ { "id": "S-0067", "title": "Verification Plan", "authors": "R. Dean", "year": 2026, "url": "https://ai-2040.com/supplements/verification-plan", "path": "/sources/dean-verification-plan/" }, { "id": "S-1301", "title": "Traffic Shaping for Workload Classification", "authors": "Lucid Computing", "year": 2026, "url": "https://lucidcomputing.substack.com/p/traffic-shaping-for-workload-classification", "path": "/sources/lucid-traffic-shaping-workload-classification/" }, { "id": "S-0018", "title": "A System Overview for Near-Term, Low-Trust AI Compute Verification", "authors": "N. Cankaya", "year": 2026, "url": "https://intelligence.org/wp-content/uploads/2026/06/A-system-overview-for-near-term-low-trust-AI-compute-verification.pdf", "path": "/sources/cankaya-system-overview-low-trust-compute-verification/" }, { "id": "S-3220", "title": "De-risking Interconnect Limits for AI Verification", "authors": "A. Scher et al.", "year": 2026, "url": "https://techgov.intelligence.org/blog/de-risking-interconnect-limits-for-ai-verification", "path": "/sources/scher-derisking-interconnect-limits/" }, { "id": "S-1313", "title": "The Tray as a Bandwidth Boundary", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/notes/2026-03-16-dpu-bandwidth-limiter/", "path": "/sources/amodo-tray-bandwidth-boundary/" }, { "id": "S-1314", "title": "DiLoCo: Distributed Low-Communication Training of Language Models", "authors": "A. Douillard et al.", "year": 2024, "url": "https://arxiv.org/abs/2311.08105", "path": "/sources/douillard-diloco/" }, { "id": "S-0060", "title": "Does Distributed Training Undermine Compute Governance?", "authors": "R. Rahman", "year": 2026, "url": "https://arxiv.org/abs/2605.29359", "path": "/sources/rahman-distributed-training-compute-governance/" }, { "id": "S-0035", "title": "Flexible Hardware-Enabled Guarantees for AI Compute", "authors": "J. Petrie et al.", "year": 2025, "url": "https://arxiv.org/abs/2506.15093", "path": "/sources/petrie-flexible-hardware-enabled-guarantees/" }, { "id": "S-1204", "title": "Technical Options for Flexible Hardware-Enabled Guarantees", "authors": "J. Petrie & O. Aarne", "year": 2025, "url": "https://arxiv.org/abs/2506.03409", "path": "/sources/petrie-technical-options-flexheg/" }, { "id": "S-1205", "title": "International Security Applications of Flexible Hardware-Enabled Guarantees", "authors": "O. Aarne & J. Petrie", "year": 2025, "url": "https://arxiv.org/abs/2506.15100", "path": "/sources/aarne-international-security-applications-flexheg/" }, { "id": "S-0057", "title": "Hardware-Enabled Governance Mechanisms: Developing Technical Solutions to Exempt Items Otherwise Classified Under Export Control Classification Numbers 3A090 and 4A090", "authors": "G. Kulp et al.", "year": 2024, "url": "https://www.rand.org/pubs/working_papers/WRA3056-1.html", "path": "/sources/kulp-hardware-enabled-governance-mechanisms/" }, { "id": "S-0056", "title": "Secure, Governable Chips: Using On-Chip Mechanisms to Manage National Security Risks from AI & Advanced Computing", "authors": "O. Aarne et al.", "year": 2024, "url": "https://www.cnas.org/publications/reports/secure-governable-chips", "path": "/sources/aarne-secure-governable-chips/" }, { "id": "S-0006", "title": "Hardware-Enabled Mechanisms for Verifying Responsible AI Development", "authors": "A. O'Gara et al.", "year": 2025, "url": "https://arxiv.org/abs/2505.03742", "path": "/sources/ogara-hardware-enabled-verifying-responsible-ai/" }, { "id": "S-0002", "title": "Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment", "authors": "M. Baker et al.", "year": 2025, "url": "https://www.rand.org/pubs/working_papers/WRA4077-1.html", "path": "/sources/baker-verifying-international-agreements-ai/" }, { "id": "S-1402", "title": "Near-Term Verification Methods for AI Chip Exports", "authors": "B. Avellar & E. Grunewald", "year": 2026, "url": "https://www.iaps.ai/research/near-term-verification-methods-for-ai-chip-exports", "path": "/sources/avellar-near-term-verification-ai-chip-exports/" }, { "id": "S-1408", "title": "TSMC most definitely has a golden record of all AI chips it made", "authors": "N. Cankaya", "year": 2025, "url": "https://nacicankaya.substack.com/p/tsmc-most-definitely-has-a-golden", "path": "/sources/cankaya-tsmc-golden-record/" }, { "id": "S-0007", "title": "Hardware-Level Governance of AI Compute: A Feasibility Taxonomy for Regulatory Compliance and Treaty Verification", "authors": "S. Ansari", "year": 2026, "url": "https://arxiv.org/abs/2604.04712", "path": "/sources/ansari-hardware-level-governance-ai-compute/" }, { "id": "S-1410", "title": "Covert AI Projects", "authors": "B. Halstead & T. Larsen", "year": 2026, "url": "https://ai-2040.com/supplements/covert-ai-projects", "path": "/sources/halstead-covert-ai-projects/" }, { "id": "S-1300", "title": "Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors", "authors": "N. Cankaya et al.", "year": 2026, "url": "https://arxiv.org/abs/2606.10724", "path": "/sources/cankaya-fingerprinting-ai-cluster-io/" }, { "id": "S-0031", "title": "The Fundamentals and Feasibility of Secure Network Taps for Verifying AI Datacenter Use", "authors": "N. Cankaya", "year": 2026, "url": "https://nacicankaya.substack.com/p/research-note-the-fundamentals-and", "path": "/sources/cankaya-secure-network-taps/" }, { "id": "S-1312", "title": "Fitting a Network TAP to our Inference Verification Prototype", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/notes/2026-09-15-network-tap-inference-verification/", "path": "/sources/amodo-network-tap-inference-verification-prototype/" }, { "id": "S-1007", "title": "Amodo-Design/Inference-Recomputation-Prototype (GitHub repository)", "authors": "Amodo Design", "year": 2026, "url": "https://github.com/Amodo-Design/Inference-Recomputation-Prototype", "path": "/sources/amodo-inference-recomputation-prototype-code/" }, { "id": "S-1319", "title": "inference-verification: Inference Verification Prototype", "authors": "Singapore AI Safety Hub (SASH)", "year": 2026, "url": "https://github.com/sg-ai-safety-hub/inference-verification", "path": "/sources/sash-inference-verification-repo/" }, { "id": "S-1320", "title": "Internationalising AI Verification", "authors": "Singapore AI Safety Hub (SASH)", "year": 2026, "url": "https://www.aisafety.sg/research/internationalising-ai-verification", "path": "/sources/sash-internationalising-ai-verification/" }, { "id": "S-1507", "title": "Adversarial Entropy Inflation Against Gumbel-Based Inference Verification", "authors": "N. Kezins", "year": 2026, "url": "https://arxiv.org/abs/2608.23375", "path": "/sources/kezins-adversarial-entropy-inflation/" }, { "id": "S-1310", "title": "Network Tapping for AI Verification: A Technical Assessment", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/notes/2026-05-03-network-tapping/", "path": "/sources/amodo-network-tapping-technical-assessment/" }, { "id": "S-1311", "title": "Network Traffic Hashing", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/notes/2026-07-03-network-traffic-hashing/", "path": "/sources/amodo-network-traffic-hashing/" } ] }