{
  "schema_version": "1.3",
  "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0012,M-0001&onsite=no",
  "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": "no",
    "coop": "",
    "chips": "",
    "ready": "",
    "tested": "",
    "hide": []
  },
  "mechanisms_passing_filters": 19,
  "claims": [],
  "mechanisms": [
    {
      "id": "M-0012",
      "title": "Hardware-attested weight binding",
      "url": "https://trustbutveri.fyi/mechanisms/model-identity-attestation/",
      "assessment_record": {
        "id": "M-0012",
        "title": "Hardware-attested weight binding",
        "url": "https://trustbutveri.fyi/mechanisms/model-identity-attestation/"
      },
      "finding_counts": {
        "failure": 2,
        "scope_limitation": 1,
        "open_question": 0,
        "open_failures": {
          "critical": 1,
          "significant": 0,
          "minor": 0
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R3",
        "scope": "hardware-attested weight binding showing users that a service runs its committed weights",
        "confidence": "medium",
        "evidence": [
          "S-0013",
          "S-0012",
          "S-1206",
          "S-1207",
          "S-1208",
          "S-1209",
          "S-1202"
        ]
      },
      "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
        }
      },
      "assessed_properties": {
        "threat_model": "semi-trusted",
        "hardware_requirement": "existing-features",
        "prover_cooperation": "required",
        "adversarial_evaluation": "independent-red-team"
      },
      "claims": [],
      "exposure": {
        "weights": "hidden",
        "io": "unknown",
        "training": "none",
        "note": "Verifiers check a hash commitment to the weights, carried in a hardware attestation, and need no access to the weights themselves. The mechanism does not specify whether prompts and outputs are disclosed to a verifier. It involves no training data.",
        "sources": [
          "S-0013",
          "S-0012",
          "S-0009"
        ]
      },
      "family_finding_context": [],
      "filter_issues": []
    },
    {
      "id": "M-0001",
      "title": "Sampled inference recomputation",
      "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/",
      "assessment_record": {
        "id": "M-0001",
        "title": "Sampled inference recomputation",
        "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/"
      },
      "finding_counts": {
        "failure": 3,
        "scope_limitation": 1,
        "open_question": 0,
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 1
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R3",
        "scope": "checking untrusted workers' activations against the declared model, prompt and precision",
        "confidence": "low",
        "evidence": [
          "S-0015",
          "S-0016",
          "S-1000",
          "S-1001",
          "S-1003",
          "S-1005",
          "S-1006",
          "S-1008",
          "S-1507",
          "S-3000",
          "S-3001"
        ]
      },
      "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
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "none",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "partial",
        "io": "partial",
        "training": "none",
        "note": "Recomputation needs the weights and sampled requests inside the checking environment. For closed models, the record describes a trusted, confidential environment; disclosure to the verifier depends on that boundary.",
        "sources": [
          "S-0016",
          "S-0017",
          "S-0018"
        ]
      },
      "family_finding_context": [],
      "filter_issues": []
    }
  ],
  "strengths": {
    "covered": [],
    "production": [
      "M-0012",
      "M-0001"
    ],
    "operationalUse": [
      "M-0012",
      "M-0001"
    ],
    "adversarial": [
      "M-0001"
    ],
    "noNewHardware": [
      "M-0012",
      "M-0001"
    ],
    "mitigated": [
      {
        "mech": "M-0012",
        "n": 2,
        "historical": false,
        "title": "Launch-state attestation does not by itself cover weights loaded later",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "mitigated",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Attestation measures launch state, and weights are read from disk after boot. A signature checked at load time does not stop a malicious hypervisor from altering the disk afterwards. Tinfoil reports mitigating this with dm-verity checks on every read. Unmeasured runtime configuration remains a general risk.",
        "response": null,
        "sources": [
          "S-0013",
          "S-0014"
        ]
      }
    ],
    "notCounted": []
  },
  "properties": {
    "covered": [],
    "production": [
      "M-0012",
      "M-0001"
    ],
    "operationalUse": [
      "M-0012",
      "M-0001"
    ],
    "adversarial": [
      "M-0001"
    ],
    "noNewHardware": [
      "M-0012",
      "M-0001"
    ],
    "mitigated": [
      {
        "mech": "M-0012",
        "n": 2,
        "historical": false,
        "title": "Launch-state attestation does not by itself cover weights loaded later",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "mitigated",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Attestation measures launch state, and weights are read from disk after boot. A signature checked at load time does not stop a malicious hypervisor from altering the disk afterwards. Tinfoil reports mitigating this with dm-verity checks on every read. Unmeasured runtime configuration remains a general risk.",
        "response": null,
        "sources": [
          "S-0013",
          "S-0014"
        ]
      }
    ],
    "notCounted": []
  },
  "attack_testing": [
    {
      "id": "M-0012",
      "record": "M-0012",
      "evaluation": "independent-red-team",
      "in_setting": true
    },
    {
      "id": "M-0001",
      "record": "M-0001",
      "evaluation": "analysis",
      "in_setting": true
    }
  ],
  "selected_implementations": {},
  "weaknesses": {
    "gaps": [],
    "excluded": [],
    "unlinked": [],
    "critical": [
      {
        "mech": "M-0012",
        "n": 1,
        "historical": false,
        "title": "Underlying attestation can be forged or relayed",
        "classification": "failure",
        "kind": "demonstrated-attack",
        "severity": "critical",
        "status": "open",
        "evidence_scope": "inherited",
        "scope_note": "Critical for weight binding against an operator with physical access to affected hardware, or with control of the hypervisor on an AMD SEV-SNP platform without AMD's fixes. PAL*M excludes physical attacks, and Tinfoil acknowledges this boundary.",
        "related_finding": {
          "record": "M-0008",
          "flaw": 1
        },
        "description": "The enclave route inherits the platform-specific TEE attestation failures. Intel TDX forgery and H100 relay were demonstrated with physical access and host control. Battering RAM defeated AMD SEV-SNP attestation on DDR4 servers; RMPocalypse did so from malicious host software on platforms without AMD's fixes. These demonstrate failures of the trust roots, not of each model-commitment protocol.",
        "response": "The TEE.fail authors report that physical interposer attacks are outside Intel's and AMD's threat models. AMD reports fixes for RMPocalypse.",
        "sources": [
          "S-1202",
          "S-1210",
          "S-1212",
          "S-1213",
          "S-1206",
          "S-0012"
        ],
        "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."
          }
        ]
      }
    ],
    "significant": [
      {
        "mech": "M-0001",
        "n": 1,
        "historical": false,
        "title": "Tolerance for numerical noise leaves a covert channel",
        "classification": "failure",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Schemes that accept approximate matches can put an upper bound on an adversary's covert bandwidth, but they cannot close the channel. The weight-exfiltration detector cut exfiltratable information to under 0.5%, not to zero, on a 30-billion-parameter mixture-of-experts model under benign prompt traffic. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token. Across six models, that cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target the check that outputs match the declared model.",
        "response": null,
        "sources": [
          "S-0020",
          "S-0015",
          "S-1507"
        ],
        "helps": [
          {
            "by": "M-0002",
            "how": "Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration."
          }
        ]
      },
      {
        "mech": "M-0001",
        "n": 3,
        "historical": false,
        "title": "Some inference optimizations are not covered",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "TOPLOC's authors state that it cannot detect speculative decoding in which a cheaper model does the decoding. They did not test whether it distinguishes types of key-value (KV) cache compression. DiFR was evaluated only on sampling from a single model. Its authors sketch an extension to one speculative-decoding algorithm but do not test it.",
        "response": null,
        "sources": [
          "S-1000",
          "S-0016"
        ]
      }
    ],
    "criticalMechanisms": [
      "M-0012"
    ],
    "significantMechanisms": [
      "M-0001"
    ],
    "familyContext": [],
    "scopeLimitations": [
      {
        "mech": "M-0012",
        "n": 3,
        "historical": false,
        "title": "For private models, a user can confirm consistency but not content",
        "classification": "scope-limitation",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "When weights are not published, users can check that the same root hash is served each time, but not what the model is. Pairing the hash with an attested evaluation, as in Attestable Audits, is one proposed remedy.",
        "response": null,
        "sources": [
          "S-0013",
          "S-0009"
        ]
      },
      {
        "mech": "M-0001",
        "n": 2,
        "historical": false,
        "title": "Only recorded traffic is checked",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Recomputation checks that recorded, declared workloads are correct. It cannot show that the record is complete. The published schemes do not cover hidden workloads run on the same compute, or substituted work. Rinberg et al. say their exfiltration-detection scheme cannot stand alone.",
        "response": null,
        "sources": [
          "S-0017",
          "S-0015"
        ],
        "helps": [
          {
            "by": "M-0013",
            "how": "Taps copy and hash all traffic on the monitored links, which bears on whether the traffic record is complete. They do not show what else ran on the same chips."
          }
        ]
      }
    ],
    "openQuestions": [],
    "minor": 1,
    "minorFindings": [
      {
        "mech": "M-0001",
        "n": 4,
        "historical": false,
        "title": "Mixed hardware widens the honest baseline",
        "classification": "failure",
        "kind": "open-question",
        "severity": "minor",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "When honest reference runs span different GPU types, the spread of benign scores grows. In DiFR's tests on Qwen3-30B-A3B, pooling A100 and H200 runs left Token-DiFR unable to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy separated them. Matched provider and verifier environments, or pooling that weights rare large deviations, restored detection.",
        "response": null,
        "sources": [
          "S-0016"
        ]
      }
    ],
    "minorBy": [
      {
        "id": "M-0001",
        "n": 1
      }
    ],
    "notDemonstrated": [],
    "newChip": []
  },
  "findings": [
    {
      "mech": "M-0012",
      "record": "M-0012",
      "n": 1,
      "historical": false,
      "title": "Underlying attestation can be forged or relayed",
      "classification": "failure",
      "kind": "demonstrated-attack",
      "severity": "critical",
      "status": "open",
      "evidence_scope": "inherited",
      "scope_note": "Critical for weight binding against an operator with physical access to affected hardware, or with control of the hypervisor on an AMD SEV-SNP platform without AMD's fixes. PAL*M excludes physical attacks, and Tinfoil acknowledges this boundary.",
      "related_finding": {
        "record": "M-0008",
        "flaw": 1
      },
      "description": "The enclave route inherits the platform-specific TEE attestation failures. Intel TDX forgery and H100 relay were demonstrated with physical access and host control. Battering RAM defeated AMD SEV-SNP attestation on DDR4 servers; RMPocalypse did so from malicious host software on platforms without AMD's fixes. These demonstrate failures of the trust roots, not of each model-commitment protocol.",
      "response": "The TEE.fail authors report that physical interposer attacks are outside Intel's and AMD's threat models. AMD reports fixes for RMPocalypse.",
      "sources": [
        "S-1202",
        "S-1210",
        "S-1212",
        "S-1213",
        "S-1206",
        "S-0012"
      ],
      "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-0012",
      "record": "M-0012",
      "n": 2,
      "historical": false,
      "title": "Launch-state attestation does not by itself cover weights loaded later",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "mitigated",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Attestation measures launch state, and weights are read from disk after boot. A signature checked at load time does not stop a malicious hypervisor from altering the disk afterwards. Tinfoil reports mitigating this with dm-verity checks on every read. Unmeasured runtime configuration remains a general risk.",
      "response": null,
      "sources": [
        "S-0013",
        "S-0014"
      ]
    },
    {
      "mech": "M-0012",
      "record": "M-0012",
      "n": 3,
      "historical": false,
      "title": "For private models, a user can confirm consistency but not content",
      "classification": "scope-limitation",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "When weights are not published, users can check that the same root hash is served each time, but not what the model is. Pairing the hash with an attested evaluation, as in Attestable Audits, is one proposed remedy.",
      "response": null,
      "sources": [
        "S-0013",
        "S-0009"
      ]
    },
    {
      "mech": "M-0001",
      "record": "M-0001",
      "n": 1,
      "historical": false,
      "title": "Tolerance for numerical noise leaves a covert channel",
      "classification": "failure",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Schemes that accept approximate matches can put an upper bound on an adversary's covert bandwidth, but they cannot close the channel. The weight-exfiltration detector cut exfiltratable information to under 0.5%, not to zero, on a 30-billion-parameter mixture-of-experts model under benign prompt traffic. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token. Across six models, that cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target the check that outputs match the declared model.",
      "response": null,
      "sources": [
        "S-0020",
        "S-0015",
        "S-1507"
      ],
      "helps": [
        {
          "by": "M-0002",
          "how": "Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration."
        }
      ]
    },
    {
      "mech": "M-0001",
      "record": "M-0001",
      "n": 2,
      "historical": false,
      "title": "Only recorded traffic is checked",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Recomputation checks that recorded, declared workloads are correct. It cannot show that the record is complete. The published schemes do not cover hidden workloads run on the same compute, or substituted work. Rinberg et al. say their exfiltration-detection scheme cannot stand alone.",
      "response": null,
      "sources": [
        "S-0017",
        "S-0015"
      ],
      "helps": [
        {
          "by": "M-0013",
          "how": "Taps copy and hash all traffic on the monitored links, which bears on whether the traffic record is complete. They do not show what else ran on the same chips."
        }
      ]
    },
    {
      "mech": "M-0001",
      "record": "M-0001",
      "n": 3,
      "historical": false,
      "title": "Some inference optimizations are not covered",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "TOPLOC's authors state that it cannot detect speculative decoding in which a cheaper model does the decoding. They did not test whether it distinguishes types of key-value (KV) cache compression. DiFR was evaluated only on sampling from a single model. Its authors sketch an extension to one speculative-decoding algorithm but do not test it.",
      "response": null,
      "sources": [
        "S-1000",
        "S-0016"
      ]
    },
    {
      "mech": "M-0001",
      "record": "M-0001",
      "n": 4,
      "historical": false,
      "title": "Mixed hardware widens the honest baseline",
      "classification": "failure",
      "kind": "open-question",
      "severity": "minor",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "When honest reference runs span different GPU types, the spread of benign scores grows. In DiFR's tests on Qwen3-30B-A3B, pooling A100 and H200 runs left Token-DiFR unable to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy separated them. Matched provider and verifier environments, or pooling that weights rare large deviations, restored detection.",
      "response": null,
      "sources": [
        "S-0016"
      ]
    }
  ],
  "possible_additions": [
    {
      "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-0012",
          "n": 1,
          "title": "Underlying attestation can be forged or relayed",
          "severity": "critical",
          "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-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-0001",
          "n": 1,
          "title": "Tolerance for numerical noise leaves a covert channel",
          "severity": "significant",
          "how": "Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration."
        }
      ]
    },
    {
      "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-0012",
          "text": "Attestation that resists physical attackers, for the enclave variant."
        }
      ]
    },
    {
      "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": false,
      "filter_issues": [
        {
          "filter": "onsite",
          "level": "exclude",
          "short": "needs a device on site",
          "text": "Needs a verifier device at the prover's site, which the filter rules out."
        }
      ],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0001",
          "text": "In tap-based retrofit designs, recording all inference traffic needs network taps and recomputation servers that can ingest it, in the worst case one recomputation-server network interface per inference front-end interface."
        }
      ]
    }
  ],
  "goal": null,
  "design": null,
  "dependencies": {
    "prerequisites": [
      {
        "id": "M-0008",
        "neededBy": [
          "M-0012"
        ]
      }
    ],
    "shared": [],
    "blockers": [
      {
        "mech": "M-0012",
        "n": 1,
        "historical": false,
        "text": "Attestation that resists physical attackers, for the enclave variant.",
        "theme": "hardware-trust",
        "blocked_by": "M-0008",
        "sources": [
          "S-1202"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0001",
        "n": 1,
        "historical": false,
        "text": "In tap-based retrofit designs, recording all inference traffic needs network taps and recomputation servers that can ingest it, in the worst case one recomputation-server network interface per inference front-end interface.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0013",
        "sources": [
          "S-1008",
          "S-0067"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0001",
        "n": 2,
        "historical": false,
        "text": "In retrofit designs, the recomputation server must sit inside the prover's data centre, possibly under the prover's physical control, and still be protected from a compromised provider, which Amodo rates 'not on track'.",
        "theme": "hardware-trust",
        "blocked_by": null,
        "sources": [
          "S-1008",
          "S-0015"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 3,
        "historical": false,
        "text": "No independent red-team of a recomputation consistency check has been published (the one independent attack study targets the weight-exfiltration bound), and Amodo rates recomputation red-teaming 'not started'.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-1008",
          "S-1507"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 4,
        "historical": false,
        "text": "Tolerance-based checks need calibration on trusted hardware and exact knowledge of the provider's sampling procedure, and in one prototype a sampling-implementation mismatch produced large spurious differences.",
        "theme": "performance-compatibility",
        "blocked_by": null,
        "sources": [
          "S-0016",
          "S-1006"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 5,
        "historical": false,
        "text": "The verifier needs the model weights, so checking a closed-weights model requires a trusted, confidential recomputation environment, which the retrofit designs place inside the prover's facility.",
        "theme": "privacy-leakage",
        "blocked_by": null,
        "sources": [
          "S-0016",
          "S-0017",
          "S-0018"
        ],
        "inProposal": null
      }
    ]
  },
  "exposure": {
    "weights": {
      "shown": [],
      "partial": [
        "M-0001"
      ],
      "hidden": [
        "M-0012"
      ],
      "none": [],
      "unknown": []
    },
    "io": {
      "shown": [],
      "partial": [
        "M-0001"
      ],
      "hidden": [],
      "none": [],
      "unknown": [
        "M-0012"
      ]
    },
    "training": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0012",
        "M-0001"
      ],
      "unknown": []
    }
  },
  "implementations": [
    {
      "mechanism": "M-0012",
      "selected": null,
      "implementations": [
        {
          "id": "I-0007",
          "title": "Attestable Audits",
          "url": "https://trustbutveri.fyi/implementations/attestable-audits/"
        },
        {
          "id": "I-0022",
          "title": "PAL*M",
          "url": "https://trustbutveri.fyi/implementations/palm/"
        },
        {
          "id": "I-0006",
          "title": "Tinfoil model identity (Modelwrap)",
          "url": "https://trustbutveri.fyi/implementations/tinfoil-model-identity/"
        }
      ]
    },
    {
      "mechanism": "M-0001",
      "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-0002",
          "title": "DiFR (Divergence From Reference)",
          "url": "https://trustbutveri.fyi/implementations/difr/"
        },
        {
          "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/"
        },
        {
          "id": "I-0001",
          "title": "TOPLOC",
          "url": "https://trustbutveri.fyi/implementations/toploc/"
        }
      ]
    }
  ],
  "sources": [
    {
      "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/"
    },
    {
      "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-1206",
      "title": "A primer on secure enclaves",
      "authors": "Tinfoil",
      "year": 2026,
      "url": "https://docs.tinfoil.sh/verification/secure-enclave-primer",
      "path": "/sources/tinfoil-docs-secure-enclave-primer/"
    },
    {
      "id": "S-1207",
      "title": "Backend infrastructure",
      "authors": "Tinfoil",
      "year": 2026,
      "url": "https://docs.tinfoil.sh/verification/attestation-architecture",
      "path": "/sources/tinfoil-docs-attestation-architecture/"
    },
    {
      "id": "S-1208",
      "title": "How verification works in Tinfoil",
      "authors": "Tinfoil",
      "year": 2026,
      "url": "https://docs.tinfoil.sh/verification/verification-in-tinfoil",
      "path": "/sources/tinfoil-docs-verification-in-tinfoil/"
    },
    {
      "id": "S-1209",
      "title": "modelwrap: Reproducible dm-verity read-only image of Huggingface models",
      "authors": "Tinfoil",
      "year": 2026,
      "url": "https://github.com/tinfoilsh/modelwrap",
      "path": "/sources/tinfoil-modelwrap-code/"
    },
    {
      "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-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-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-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-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-0016",
      "title": "DiFR: Inference Verification Despite Nondeterminism",
      "authors": "A. Karvonen et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2511.20621",
      "path": "/sources/karvonen-difr/"
    },
    {
      "id": "S-1000",
      "title": "TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference",
      "authors": "J. M. Ong et al.",
      "year": 2025,
      "url": "https://proceedings.mlr.press/v267/ong25a.html",
      "path": "/sources/ong-toploc/"
    },
    {
      "id": "S-1001",
      "title": "PrimeIntellect-ai/toploc (GitHub repository)",
      "authors": "Prime Intellect",
      "year": 2025,
      "url": "https://github.com/PrimeIntellect-ai/toploc",
      "path": "/sources/primeintellect-toploc-code/"
    },
    {
      "id": "S-1003",
      "title": "INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning",
      "authors": "Prime Intellect Team et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2505.07291",
      "path": "/sources/primeintellect-intellect-2/"
    },
    {
      "id": "S-1005",
      "title": "adamkarvonen/difr (GitHub repository)",
      "authors": "A. Karvonen",
      "year": 2025,
      "url": "https://github.com/adamkarvonen/difr",
      "path": "/sources/karvonen-difr-code/"
    },
    {
      "id": "S-1006",
      "title": "Scaling Recomputation Inference Verification",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/notes/2026-09-02-scaling-recomputation-inference-verification/",
      "path": "/sources/amodo-scaling-recomputation-inference-verification/"
    },
    {
      "id": "S-1008",
      "title": "AI 2040 Plan A — Verification SITREP",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/ai-verification/plan-a-sitrep/",
      "path": "/sources/amodo-plan-a-verification-sitrep/"
    },
    {
      "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-3000",
      "title": "SYNTHETIC-2 Release: Four Million Collaboratively Generated Reasoning Traces",
      "authors": "Prime Intellect",
      "year": 2025,
      "url": "https://www.primeintellect.ai/blog/synthetic-2-release",
      "path": "/sources/primeintellect-synthetic-2-release/"
    },
    {
      "id": "S-3001",
      "title": "An Inference Verification Prototype — Stage 1",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/notes/2026-06-29-inference-verification-prototype/",
      "path": "/sources/amodo-inference-verification-prototype-stage-1/"
    },
    {
      "id": "S-0020",
      "title": "Bit-Exact AI Inference Verification Without Performance Tradeoffs",
      "authors": "N. Cankaya",
      "year": 2026,
      "url": "https://arxiv.org/abs/2606.00279",
      "path": "/sources/cankaya-bit-exact-inference-verification/"
    },
    {
      "id": "S-0017",
      "title": "Example Schemes for Verifying High-Stakes AI Agreements",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/notes/2026-06-23-verification-algorithms/",
      "path": "/sources/amodo-example-schemes-high-stakes-ai-agreements/"
    },
    {
      "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-0067",
      "title": "Verification Plan",
      "authors": "R. Dean",
      "year": 2026,
      "url": "https://ai-2040.com/supplements/verification-plan",
      "path": "/sources/dean-verification-plan/"
    }
  ]
}