{
  "schema_version": "1.3",
  "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0023,M-0024,M-0014&cols=hardware",
  "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-0023",
      "title": "Safeguard attestation",
      "url": "https://trustbutveri.fyi/mechanisms/safeguard-attestation/",
      "assessment_record": {
        "id": "M-0023",
        "title": "Safeguard attestation",
        "url": "https://trustbutveri.fyi/mechanisms/safeguard-attestation/"
      },
      "finding_counts": {
        "failure": 2,
        "scope_limitation": 3,
        "open_question": 0,
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 0
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R2",
        "scope": "attesting that a declared safeguard mediated a service's responses",
        "confidence": "low",
        "evidence": [
          "S-1500",
          "S-1501",
          "S-3362",
          "S-0012",
          "S-1503",
          "S-1504",
          "S-1202",
          "S-3126"
        ]
      },
      "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": 4,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1500",
              "S-1501"
            ]
          },
          {
            "n": 5,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "inherited",
            "sources": [
              "S-1202",
              "S-3126",
              "S-1210",
              "S-1212",
              "S-1213",
              "S-0012",
              "S-0014",
              "S-1500",
              "S-0018"
            ],
            "related_finding": {
              "record": "M-0008",
              "flaw": 1
            }
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 0
        }
      },
      "assessed_properties": {
        "threat_model": "semi-trusted",
        "hardware_requirement": "existing-features",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "partial",
        "io": "partial",
        "training": "none",
        "note": "The enclave route signs hashes of the safeguard, request and response; a low-trust design has the verifier re-run and screen sampled requests itself."
      },
      "family_finding_context": [],
      "filter_issues": []
    },
    {
      "id": "M-0024",
      "title": "Bounding unexplained information in outputs",
      "url": "https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/",
      "assessment_record": {
        "id": "M-0024",
        "title": "Bounding unexplained information in outputs",
        "url": "https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/"
      },
      "finding_counts": {
        "failure": 1,
        "scope_limitation": 2,
        "open_question": 1,
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R2",
        "scope": "bounding how much hidden information can leave in checked inference outputs",
        "confidence": "low",
        "evidence": [
          "S-0019",
          "S-0015",
          "S-1507"
        ]
      },
      "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
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "retrofit-device",
        "prover_cooperation": "required",
        "adversarial_evaluation": "independent-red-team"
      },
      "claims": [],
      "exposure": {
        "weights": "partial",
        "io": "partial",
        "training": "none",
        "note": "Depends on where recomputation runs: in a sealed enclosure, or with zero-knowledge proofs, the verifier need not see the weights or the traffic."
      },
      "family_finding_context": [],
      "filter_issues": []
    },
    {
      "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": []
    }
  ],
  "strengths": {
    "covered": [],
    "production": [],
    "operationalUse": [],
    "adversarial": [
      "M-0024",
      "M-0014"
    ],
    "noNewHardware": [
      "M-0023"
    ],
    "mitigated": [],
    "notCounted": []
  },
  "properties": {
    "covered": [],
    "production": [],
    "operationalUse": [],
    "adversarial": [
      "M-0024",
      "M-0014"
    ],
    "noNewHardware": [
      "M-0023"
    ],
    "mitigated": [],
    "notCounted": []
  },
  "attack_testing": [
    {
      "id": "M-0023",
      "record": "M-0023",
      "evaluation": "analysis",
      "in_setting": true
    },
    {
      "id": "M-0024",
      "record": "M-0024",
      "evaluation": "independent-red-team",
      "in_setting": true
    },
    {
      "id": "M-0014",
      "record": "M-0014",
      "evaluation": "analysis",
      "in_setting": true
    }
  ],
  "selected_implementations": {},
  "weaknesses": {
    "gaps": [],
    "excluded": [],
    "unlinked": [],
    "critical": [],
    "significant": [
      {
        "mech": "M-0023",
        "n": 4,
        "historical": false,
        "title": "Components outside the attested boundary",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "In the proof-of-guardrail experiments, the guardrail model and the agent's backend model were both reached through external APIs, and the authors leave the decision to trust those APIs to the verifier. The measured wrapper must also have no vulnerability that lets the unmeasured agent bypass the guardrail, for example by executing arbitrary commands inside the enclave. The code's README states that the enclave does not currently restrict the agent's arbitrary command execution, which could be used to bypass guardrails.",
        "response": null,
        "sources": [
          "S-1500",
          "S-1501"
        ]
      },
      {
        "mech": "M-0023",
        "n": 5,
        "historical": false,
        "title": "Memory-bus interposition extracts attestation keys and forges attestations",
        "classification": "failure",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": "inherited",
        "scope_note": "Applies to variants using the affected Intel or AMD trust roots. PAL*M excludes physical attacks. A TDX-backed safeguard claim against a physical host attacker would be defeated, but these studies do not demonstrate a break of the AWS Nitro proof-of-guardrail prototype or of verifier-side recomputation.",
        "related_finding": {
          "record": "M-0008",
          "flaw": 1
        },
        "description": "The TEE findings cover DDR5 attacks on Intel TDX, the H100 relay demonstration, DDR4 attacks on AMD SEV-SNP, and software-only SEV-SNP forgery before AMD's fixes. These are inherited hardware limits; a governance analysis explains why physical access matters in a treaty setting.",
        "response": "Intel and AMD place the physical attack class outside their threat models, according to the researchers. AMD reports firmware fixes for RMPocalypse.",
        "sources": [
          "S-1202",
          "S-3126",
          "S-1210",
          "S-1212",
          "S-1213",
          "S-0012",
          "S-0014",
          "S-1500",
          "S-0018"
        ],
        "helps": [
          {
            "by": "M-0009",
            "how": "A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically."
          }
        ]
      },
      {
        "mech": "M-0024",
        "n": 1,
        "historical": false,
        "title": "Prompt-controlled entropy inflation widens the covert channel",
        "classification": "failure",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Gumbel-based inference verification tolerates token choices that honest GPU nondeterminism could produce, and the size of that tolerated set grows with the model's output entropy. Kezins, an independent researcher, showed that an adversary who controls the prompt distribution can raise output entropy and roughly double the bits leaked per token. Across six models of 1 to 32 billion parameters, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. Kezins argues that architectures built on the same unexplained-information bound inherit this attack surface, and recommends calibrating tolerances against local token entropy rather than benign traffic.",
        "response": null,
        "sources": [
          "S-1507",
          "S-0015"
        ],
        "helps": [
          {
            "by": "M-0002",
            "how": "Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata."
          }
        ]
      },
      {
        "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"
        ]
      }
    ],
    "criticalMechanisms": [],
    "significantMechanisms": [
      "M-0023",
      "M-0024",
      "M-0014"
    ],
    "familyContext": [],
    "scopeLimitations": [
      {
        "mech": "M-0023",
        "n": 1,
        "historical": false,
        "title": "Attestation shows a safeguard ran, not that it is effective",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Proof of guardrail ensures that the guardrail executed, but the guardrail can still err or be jailbroken. Because the guardrail must be open source, a malicious developer can attack it with jailbreaks while still presenting a valid proof. In the authors' evaluation, Llama Guard 3 reached an F1 score of 0.56 on the unsafe class of the ToxicChat dataset. The authors state that proof of guardrail should not be interpreted or advertised as proof of safety.",
        "response": null,
        "sources": [
          "S-1500"
        ]
      },
      {
        "mech": "M-0023",
        "n": 2,
        "historical": false,
        "title": "Selective attestation leaves traffic uncovered",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Attestations are issued per response. In the prototype, the agent offers them when it receives high-stakes questions, so nothing shows that unattested traffic went through the same path. PAL*M's authors note that a prover could cherry-pick favourable executions, and suggest verifier-published nonces or requesting only session-level proofs. A governance analysis notes that auditors also need assurance that all activity is accounted for, since a host could start a second confidential virtual machine that bypasses monitoring.",
        "response": null,
        "sources": [
          "S-1500",
          "S-0012",
          "S-0014"
        ],
        "helps": [
          {
            "by": "M-0010",
            "how": "On-chip counters are a proposed route to evidence about everything a chip runs, including a second virtual machine that skips the safeguard."
          }
        ]
      },
      {
        "mech": "M-0023",
        "n": 3,
        "historical": false,
        "title": "Measurements may omit behaviour-relevant configuration or runtime changes",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Every component that influences inference behaviour must be covered by the launch measurement, including feature flags, environment variables and invocation arguments. A launch measurement also does not show that a program keeps running as measured if the kernel is later compromised.",
        "response": null,
        "sources": [
          "S-0014"
        ]
      },
      {
        "mech": "M-0024",
        "n": 2,
        "historical": false,
        "title": "Information the declared computation explains is not bounded",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The bound limits unexplained bits only. Outputs that the declared computation fully explains can still carry valuable information: a compression study notes that an adversary with inference access can extract more proprietary information per bit than naive transmission allows.",
        "response": null,
        "sources": [
          "S-1508",
          "S-0019"
        ]
      },
      {
        "mech": "M-0024",
        "n": 3,
        "historical": false,
        "title": "Channels other than checked outputs are outside the bound",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The inference-verification scheme treats side channels as out of scope. A low-trust system design argues that suppressing physical covert bandwidth below kilobits per second is much more achievable than aiming for zero, and that a malicious device can leak one bit of information by deliberately outputting a wrong result.",
        "response": null,
        "sources": [
          "S-0015",
          "S-0018"
        ],
        "helps": [
          {
            "by": "M-0022",
            "how": "Physical side channels need separate suppression, which is this mechanism's purpose."
          }
        ]
      },
      {
        "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"
        ]
      }
    ],
    "openQuestions": [
      {
        "mech": "M-0024",
        "n": 4,
        "historical": false,
        "title": "The facility-level design is untested",
        "classification": "open-question",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The compute-verification architecture is described with protocol details, potential attacks and prototyping plans, but no prototype results have been published.",
        "response": null,
        "sources": [
          "S-0019"
        ]
      },
      {
        "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"
        ]
      }
    ],
    "minor": 0,
    "minorFindings": [],
    "minorBy": [],
    "notDemonstrated": [],
    "newChip": []
  },
  "findings": [
    {
      "mech": "M-0023",
      "record": "M-0023",
      "n": 1,
      "historical": false,
      "title": "Attestation shows a safeguard ran, not that it is effective",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Proof of guardrail ensures that the guardrail executed, but the guardrail can still err or be jailbroken. Because the guardrail must be open source, a malicious developer can attack it with jailbreaks while still presenting a valid proof. In the authors' evaluation, Llama Guard 3 reached an F1 score of 0.56 on the unsafe class of the ToxicChat dataset. The authors state that proof of guardrail should not be interpreted or advertised as proof of safety.",
      "response": null,
      "sources": [
        "S-1500"
      ]
    },
    {
      "mech": "M-0023",
      "record": "M-0023",
      "n": 2,
      "historical": false,
      "title": "Selective attestation leaves traffic uncovered",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Attestations are issued per response. In the prototype, the agent offers them when it receives high-stakes questions, so nothing shows that unattested traffic went through the same path. PAL*M's authors note that a prover could cherry-pick favourable executions, and suggest verifier-published nonces or requesting only session-level proofs. A governance analysis notes that auditors also need assurance that all activity is accounted for, since a host could start a second confidential virtual machine that bypasses monitoring.",
      "response": null,
      "sources": [
        "S-1500",
        "S-0012",
        "S-0014"
      ],
      "helps": [
        {
          "by": "M-0010",
          "how": "On-chip counters are a proposed route to evidence about everything a chip runs, including a second virtual machine that skips the safeguard."
        }
      ]
    },
    {
      "mech": "M-0023",
      "record": "M-0023",
      "n": 3,
      "historical": false,
      "title": "Measurements may omit behaviour-relevant configuration or runtime changes",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Every component that influences inference behaviour must be covered by the launch measurement, including feature flags, environment variables and invocation arguments. A launch measurement also does not show that a program keeps running as measured if the kernel is later compromised.",
      "response": null,
      "sources": [
        "S-0014"
      ]
    },
    {
      "mech": "M-0023",
      "record": "M-0023",
      "n": 4,
      "historical": false,
      "title": "Components outside the attested boundary",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "In the proof-of-guardrail experiments, the guardrail model and the agent's backend model were both reached through external APIs, and the authors leave the decision to trust those APIs to the verifier. The measured wrapper must also have no vulnerability that lets the unmeasured agent bypass the guardrail, for example by executing arbitrary commands inside the enclave. The code's README states that the enclave does not currently restrict the agent's arbitrary command execution, which could be used to bypass guardrails.",
      "response": null,
      "sources": [
        "S-1500",
        "S-1501"
      ]
    },
    {
      "mech": "M-0023",
      "record": "M-0023",
      "n": 5,
      "historical": false,
      "title": "Memory-bus interposition extracts attestation keys and forges attestations",
      "classification": "failure",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": "inherited",
      "scope_note": "Applies to variants using the affected Intel or AMD trust roots. PAL*M excludes physical attacks. A TDX-backed safeguard claim against a physical host attacker would be defeated, but these studies do not demonstrate a break of the AWS Nitro proof-of-guardrail prototype or of verifier-side recomputation.",
      "related_finding": {
        "record": "M-0008",
        "flaw": 1
      },
      "description": "The TEE findings cover DDR5 attacks on Intel TDX, the H100 relay demonstration, DDR4 attacks on AMD SEV-SNP, and software-only SEV-SNP forgery before AMD's fixes. These are inherited hardware limits; a governance analysis explains why physical access matters in a treaty setting.",
      "response": "Intel and AMD place the physical attack class outside their threat models, according to the researchers. AMD reports firmware fixes for RMPocalypse.",
      "sources": [
        "S-1202",
        "S-3126",
        "S-1210",
        "S-1212",
        "S-1213",
        "S-0012",
        "S-0014",
        "S-1500",
        "S-0018"
      ],
      "helps": [
        {
          "by": "M-0009",
          "how": "A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically."
        }
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 1,
      "historical": false,
      "title": "Prompt-controlled entropy inflation widens the covert channel",
      "classification": "failure",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Gumbel-based inference verification tolerates token choices that honest GPU nondeterminism could produce, and the size of that tolerated set grows with the model's output entropy. Kezins, an independent researcher, showed that an adversary who controls the prompt distribution can raise output entropy and roughly double the bits leaked per token. Across six models of 1 to 32 billion parameters, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. Kezins argues that architectures built on the same unexplained-information bound inherit this attack surface, and recommends calibrating tolerances against local token entropy rather than benign traffic.",
      "response": null,
      "sources": [
        "S-1507",
        "S-0015"
      ],
      "helps": [
        {
          "by": "M-0002",
          "how": "Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata."
        }
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 2,
      "historical": false,
      "title": "Information the declared computation explains is not bounded",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The bound limits unexplained bits only. Outputs that the declared computation fully explains can still carry valuable information: a compression study notes that an adversary with inference access can extract more proprietary information per bit than naive transmission allows.",
      "response": null,
      "sources": [
        "S-1508",
        "S-0019"
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 3,
      "historical": false,
      "title": "Channels other than checked outputs are outside the bound",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The inference-verification scheme treats side channels as out of scope. A low-trust system design argues that suppressing physical covert bandwidth below kilobits per second is much more achievable than aiming for zero, and that a malicious device can leak one bit of information by deliberately outputting a wrong result.",
      "response": null,
      "sources": [
        "S-0015",
        "S-0018"
      ],
      "helps": [
        {
          "by": "M-0022",
          "how": "Physical side channels need separate suppression, which is this mechanism's purpose."
        }
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 4,
      "historical": false,
      "title": "The facility-level design is untested",
      "classification": "open-question",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The compute-verification architecture is described with protocol details, potential attacks and prototyping plans, but no prototype results have been published.",
      "response": null,
      "sources": [
        "S-0019"
      ]
    },
    {
      "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"
      ]
    }
  ],
  "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-0024",
          "n": 1,
          "title": "Prompt-controlled entropy inflation widens the covert channel",
          "severity": "significant",
          "how": "Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata."
        },
        {
          "kind": "blocker",
          "mech": "M-0024",
          "text": "Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata."
        }
      ]
    },
    {
      "id": "M-0009",
      "title": "Hardware-enabled guarantees (flexHEG) and guarantee processors",
      "url": "https://trustbutveri.fyi/mechanisms/flexheg-guarantee-processors/",
      "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": [
          {
            "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
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "flaw",
          "mech": "M-0023",
          "n": 5,
          "title": "Memory-bus interposition extracts attestation keys and forges attestations",
          "severity": "significant",
          "how": "A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically."
        }
      ]
    },
    {
      "id": "M-0012",
      "title": "Hardware-attested weight binding",
      "url": "https://trustbutveri.fyi/mechanisms/model-identity-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": "inherited",
            "sources": [
              "S-1202",
              "S-1210",
              "S-1212",
              "S-1213",
              "S-1206",
              "S-0012"
            ],
            "related_finding": {
              "record": "M-0008",
              "flaw": 1
            }
          },
          {
            "n": 2,
            "severity": "significant",
            "status": "mitigated",
            "evidence_scope": "unassessed",
            "sources": [
              "S-0013",
              "S-0014"
            ]
          }
        ],
        "open_failures": {
          "critical": 1,
          "significant": 0,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0023",
          "text": "Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation."
        }
      ]
    },
    {
      "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": "blocker",
          "mech": "M-0023",
          "text": "Frontier model inference typically needs several GPUs, GPU confidential computing is less mature than CPU support, and CPU inference, which an enclave prototype had to use, ran about 100 times slower than GPU inference."
        },
        {
          "kind": "blocker",
          "mech": "M-0023",
          "text": "Trust rests on a small number of hardware vendors, and a per-CPU Intel attestation key has been extracted by physical attack."
        }
      ]
    },
    {
      "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."
        }
      ]
    },
    {
      "id": "M-0013",
      "title": "Network taps and certifiers",
      "url": "https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/",
      "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": [
          {
            "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
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0014",
          "text": "The verifier must know that all traffic leaving a pod crosses the capped, monitored links."
        },
        {
          "kind": "prerequisite",
          "mech": "M-0024"
        }
      ]
    },
    {
      "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-0024",
          "text": "Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target."
        }
      ]
    },
    {
      "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-0024"
        }
      ]
    }
  ],
  "goal": null,
  "design": null,
  "dependencies": {
    "prerequisites": [
      {
        "id": "M-0008",
        "neededBy": [
          "M-0023"
        ]
      },
      {
        "id": "M-0012",
        "neededBy": [
          "M-0023"
        ]
      },
      {
        "id": "M-0001",
        "neededBy": [
          "M-0024"
        ]
      },
      {
        "id": "M-0022",
        "neededBy": [
          "M-0024"
        ]
      },
      {
        "id": "M-0013",
        "neededBy": [
          "M-0024"
        ]
      },
      {
        "id": "M-0017",
        "neededBy": [
          "M-0014"
        ]
      }
    ],
    "shared": [
      {
        "id": "M-0013",
        "by": [
          "M-0024",
          "M-0014"
        ],
        "inProposal": false
      }
    ],
    "blockers": [
      {
        "mech": "M-0023",
        "n": 1,
        "historical": false,
        "text": "No published design shows that all of a provider's traffic passes through the attested safeguard path; current evidence covers individual attested responses.",
        "theme": "coverage-hidden-compute",
        "blocked_by": null,
        "sources": [
          "S-1500",
          "S-0014"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0023",
        "n": 2,
        "historical": false,
        "text": "Frontier model inference typically needs several GPUs, GPU confidential computing is less mature than CPU support, and CPU inference, which an enclave prototype had to use, ran about 100 times slower than GPU inference.",
        "theme": "performance-compatibility",
        "blocked_by": "M-0008",
        "sources": [
          "S-0014",
          "S-0009"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0023",
        "n": 3,
        "historical": false,
        "text": "Trust rests on a small number of hardware vendors, and a per-CPU Intel attestation key has been extracted by physical attack.",
        "theme": "hardware-trust",
        "blocked_by": "M-0008",
        "sources": [
          "S-0014",
          "S-1202"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0023",
        "n": 4,
        "historical": false,
        "text": "Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation.",
        "theme": "evidence-binding",
        "blocked_by": "M-0012",
        "sources": [
          "S-0009",
          "S-0013"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0023",
        "n": 5,
        "historical": false,
        "text": "No independent red-team or audit of a safeguard-attestation system has been published, and the available prototypes are described by their authors as proofs of concept that have not been stress-tested by a counterparty.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-1501",
          "S-1504"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0024",
        "n": 1,
        "historical": false,
        "text": "The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0014",
        "sources": [
          "S-0019"
        ],
        "inProposal": true
      },
      {
        "mech": "M-0024",
        "n": 2,
        "historical": false,
        "text": "Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0022",
        "sources": [
          "S-0018",
          "S-0015"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0024",
        "n": 3,
        "historical": false,
        "text": "Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata.",
        "theme": "protocol-soundness",
        "blocked_by": "M-0002",
        "sources": [
          "S-1507",
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0024",
        "n": 4,
        "historical": false,
        "text": "Recomputation over confidential weights and inputs needs a protected setting: prover recomputation in a verifier-controlled enclosure, verifier recomputation in a prover-controlled enclosure, or zero-knowledge proofs.",
        "theme": "privacy-leakage",
        "blocked_by": null,
        "sources": [
          "S-0019"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0024",
        "n": 5,
        "historical": false,
        "text": "No prototype of the facility-level architecture exists to red-team.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-0019"
        ],
        "inProposal": null
      },
      {
        "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": false
      },
      {
        "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
      }
    ]
  },
  "exposure": {
    "weights": {
      "shown": [],
      "partial": [
        "M-0023",
        "M-0024"
      ],
      "hidden": [],
      "none": [
        "M-0014"
      ],
      "unknown": []
    },
    "io": {
      "shown": [],
      "partial": [
        "M-0023",
        "M-0024"
      ],
      "hidden": [],
      "none": [
        "M-0014"
      ],
      "unknown": []
    },
    "training": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0023",
        "M-0024",
        "M-0014"
      ],
      "unknown": []
    }
  },
  "implementations": [
    {
      "mechanism": "M-0023",
      "selected": null,
      "implementations": []
    },
    {
      "mechanism": "M-0024",
      "selected": null,
      "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/"
        }
      ]
    }
  ],
  "sources": [
    {
      "id": "S-1500",
      "title": "Proof-of-Guardrail in AI Agents and What (Not) to Trust from It",
      "authors": "X. Jin et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2603.05786",
      "path": "/sources/jin-proof-of-guardrail/"
    },
    {
      "id": "S-1501",
      "title": "Verifiable-ClawGuard: proof-of-guardrail reference code",
      "authors": "SaharaLabsAI",
      "year": 2026,
      "url": "https://github.com/SaharaLabsAI/Verifiable-ClawGuard",
      "path": "/sources/sahara-verifiable-clawguard-code/"
    },
    {
      "id": "S-3362",
      "title": "Safety Without Compromising on Privacy",
      "authors": "D. McCann-Sayles et al.",
      "year": 2026,
      "url": "https://tinfoil.sh/blog/2026-09-14-safety-without-compromising-privacy",
      "path": "/sources/tinfoil-safety-without-compromising-privacy/"
    },
    {
      "id": "S-0012",
      "title": "PAL*M: Property Attestation for Large Generative Models",
      "authors": "P. Chantasantitam et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2601.16199",
      "path": "/sources/chantasantitam-palm/"
    },
    {
      "id": "S-1503",
      "title": "Enabling Verifiably-Scoped Monitoring through Large Language Models and Trusted Compute",
      "authors": "B. Penchas et al.",
      "year": 2026,
      "url": "https://icml.cc/virtual/2026/78630",
      "path": "/sources/penchas-verifiably-scoped-monitoring/"
    },
    {
      "id": "S-1504",
      "title": "Auditor-in-a-Box: Tools for Third-Party Auditing",
      "authors": "R. Rinberg & B. Penchas",
      "year": 2026,
      "url": "https://www.lesswrong.com/posts/uWYk7MM9hAf9GEbGe/auditor-in-a-box-tools-for-third-party-auditing",
      "path": "/sources/rinberg-auditor-in-a-box/"
    },
    {
      "id": "S-1202",
      "title": "TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition",
      "authors": "J. Chuang et al.",
      "year": 2026,
      "url": "https://tee.fail/",
      "path": "/sources/chuang-tee-fail/"
    },
    {
      "id": "S-3126",
      "title": "DDRop: Active Memory Interposer Attacks on Confidential VMs by Dropping DDR5 Writes",
      "authors": "J. De Meulemeester et al.",
      "year": 2026,
      "url": "https://ddropattack.eu/",
      "path": "/sources/de-meulemeester-ddrop/"
    },
    {
      "id": "S-0014",
      "title": "On TEEs for Privacy-Preserving Monitoring in AI Governance",
      "authors": "Gloria Z",
      "year": 2026,
      "url": "https://techgov.intelligence.org/blog/on-tees-for-privacy-preserving-monitoring-in-ai-governance",
      "path": "/sources/zhao-tees-privacy-preserving-monitoring/"
    },
    {
      "id": "S-1210",
      "title": "Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing",
      "authors": "J. De Meulemeester et al.",
      "year": 2026,
      "url": "https://batteringram.eu/",
      "path": "/sources/de-meulemeester-battering-ram/"
    },
    {
      "id": "S-1212",
      "title": "RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP",
      "authors": "B. Schlüter & S. Shinde",
      "year": 2025,
      "url": "https://rmpocalypse.github.io/",
      "path": "/sources/schluter-rmpocalypse/"
    },
    {
      "id": "S-1213",
      "title": "SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020)",
      "authors": "AMD",
      "year": 2025,
      "url": "https://www.amd.com/en/resources/product-security/bulletin/amd-sb-3020.html",
      "path": "/sources/amd-sb-3020-rmp-initialization/"
    },
    {
      "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-0019",
      "title": "Verifying AI Compute by Bounding Unexplained Information Exfiltration",
      "authors": "J. Petrie & Y. Mühlhäuser",
      "year": 2026,
      "url": "https://openreview.net/forum?id=qtgG5HZSsk",
      "path": "/sources/petrie-bounding-unexplained-information-exfiltration/"
    },
    {
      "id": "S-0015",
      "title": "Verifying LLM Inference to Detect Model Weight Exfiltration",
      "authors": "R. Rinberg et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2511.02620",
      "path": "/sources/rinberg-verifying-llm-inference-weight-exfiltration/"
    },
    {
      "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-1508",
      "title": "Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains",
      "authors": "R. Rinberg et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2604.02343",
      "path": "/sources/rinberg-haiku-to-opus-compression/"
    },
    {
      "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-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-0009",
      "title": "Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments",
      "authors": "C. Schnabl et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2506.23706",
      "path": "/sources/schnabl-attestable-audits/"
    },
    {
      "id": "S-0013",
      "title": "How Tinfoil Proves Exactly What Model Is Running",
      "authors": "Tinfoil Team",
      "year": 2026,
      "url": "https://tinfoil.sh/blog/2026-02-03-proving-model-identity",
      "path": "/sources/tinfoil-proving-model-identity/"
    }
  ]
}