{
  "schema_version": "1.3",
  "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0016,M-0012&implementations=M-0016:I-0012",
  "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-0016",
      "title": "Timed challenge-response and memory-occupation challenges",
      "url": "https://trustbutveri.fyi/mechanisms/timed-challenge-response/",
      "assessment_record": {
        "id": "I-0012",
        "title": "Low-trust AI compute verification system overview",
        "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
      },
      "finding_counts": {
        "failure": 1,
        "scope_limitation": 1,
        "open_question": 1,
        "open_failures": {
          "critical": 0,
          "significant": 0,
          "minor": 1
        }
      },
      "selected_implementation": {
        "id": "I-0012",
        "title": "Low-trust AI compute verification system overview",
        "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
      },
      "readiness": {
        "level": "R1",
        "scope": "screening challenged records to show declared inference compute is not training",
        "confidence": "medium",
        "evidence": [
          "S-0018",
          "S-1300"
        ]
      },
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 2,
            "severity": "minor",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-0018"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 0,
          "minor": 1
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "retrofit-device",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "unknown",
        "io": "unknown",
        "training": "unknown",
        "note": "This Explorer has no asset-specific exposure assessment for this implementation. Check its source and deployment assumptions.",
        "sources": []
      },
      "family_finding_context": [
        {
          "n": 1,
          "historical": false,
          "title": "Timing-based software attestation has been broken in practice",
          "classification": "failure",
          "kind": "demonstrated-attack",
          "severity": "significant",
          "status": "disputed",
          "evidence_scope": null,
          "scope_note": null,
          "related_finding": null,
          "description": "Castelluccia et al. implemented two generic attacks, one based on a return-oriented rootkit and one on code compression, together with specific attacks on SWATT and ICE-based schemes, on commodity sensor nodes. They conclude that secure time-based attestation is \"very difficult, if not impossible, to design correctly\". The attacks target embedded schemes, not AI accelerators.",
          "response": "Perrig and van Doorn, two of the designers of SWATT and ICE, replied in August 2010. They argue that the rootkit attack defeats a naive implementation, not a property the schemes claim, and that the SWATT attack was run on a re-implementation on a chip with eight times the program memory, where SWATT's own chip is almost always full of code. They accept that the attack on ICE works.",
          "sources": [
            "S-1308",
            "S-0074"
          ],
          "record": "M-0016",
          "represented_by": []
        },
        {
          "n": 2,
          "historical": false,
          "title": "Remote memory narrows the timing margin",
          "classification": "failure",
          "kind": "theoretical-argument",
          "severity": "significant",
          "status": "open",
          "evidence_scope": null,
          "scope_note": null,
          "related_finding": null,
          "description": "Data-centre remote memory access returns in about 1–2 µs, against about 70–200 ns for local DRAM. The MIRI overview says verification of memory saturation depends on ruling out remote access by latency or physical disconnection. It names pre-staging data into local memory as the remaining evasion and proposes an unpredictable, capacity-filling challenge to close it.",
          "response": null,
          "sources": [
            "S-0018"
          ],
          "helps": [
            {
              "by": "M-0014",
              "how": "Physical disconnection is proposed to exclude remote memory between the separated groups during a challenge. It depends on the isolation boundary being enforced."
            }
          ],
          "record": "M-0016",
          "represented_by": []
        },
        {
          "n": 3,
          "historical": false,
          "title": "Error rates not quantified",
          "classification": "open-question",
          "kind": "open-question",
          "severity": "minor",
          "status": "open",
          "evidence_scope": null,
          "scope_note": null,
          "related_finding": null,
          "description": "Monfared et al. show separable timing distributions. Their acceptance rule passes a GPU when its mean time per round stays at or below a chosen maximum, and an appendix outlines statistical tests for the proof-of-work puzzle. They leave hardware-specific threshold values to future work and report no false-positive or false-negative rates.",
          "response": null,
          "sources": [
            "S-0033"
          ],
          "record": "M-0016",
          "represented_by": []
        }
      ],
      "filter_issues": []
    },
    {
      "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": []
    }
  ],
  "strengths": {
    "covered": [],
    "production": [
      "M-0012"
    ],
    "operationalUse": [
      "M-0012"
    ],
    "adversarial": [
      "M-0016"
    ],
    "noNewHardware": [
      "M-0012"
    ],
    "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"
    ],
    "operationalUse": [
      "M-0012"
    ],
    "adversarial": [
      "M-0016"
    ],
    "noNewHardware": [
      "M-0012"
    ],
    "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-0016",
      "record": "I-0012",
      "evaluation": "analysis",
      "in_setting": true
    },
    {
      "id": "M-0012",
      "record": "M-0012",
      "evaluation": "independent-red-team",
      "in_setting": true
    }
  ],
  "selected_implementations": {
    "M-0016": "I-0012"
  },
  "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": [],
    "criticalMechanisms": [
      "M-0012"
    ],
    "significantMechanisms": [],
    "familyContext": [
      {
        "id": "M-0016",
        "implementation": "I-0012",
        "flaws": [
          {
            "n": 1,
            "historical": false,
            "title": "Timing-based software attestation has been broken in practice",
            "classification": "failure",
            "kind": "demonstrated-attack",
            "severity": "significant",
            "status": "disputed",
            "evidence_scope": null,
            "scope_note": null,
            "related_finding": null,
            "description": "Castelluccia et al. implemented two generic attacks, one based on a return-oriented rootkit and one on code compression, together with specific attacks on SWATT and ICE-based schemes, on commodity sensor nodes. They conclude that secure time-based attestation is \"very difficult, if not impossible, to design correctly\". The attacks target embedded schemes, not AI accelerators.",
            "response": "Perrig and van Doorn, two of the designers of SWATT and ICE, replied in August 2010. They argue that the rootkit attack defeats a naive implementation, not a property the schemes claim, and that the SWATT attack was run on a re-implementation on a chip with eight times the program memory, where SWATT's own chip is almost always full of code. They accept that the attack on ICE works.",
            "sources": [
              "S-1308",
              "S-0074"
            ],
            "record": "M-0016",
            "represented_by": []
          },
          {
            "n": 2,
            "historical": false,
            "title": "Remote memory narrows the timing margin",
            "classification": "failure",
            "kind": "theoretical-argument",
            "severity": "significant",
            "status": "open",
            "evidence_scope": null,
            "scope_note": null,
            "related_finding": null,
            "description": "Data-centre remote memory access returns in about 1–2 µs, against about 70–200 ns for local DRAM. The MIRI overview says verification of memory saturation depends on ruling out remote access by latency or physical disconnection. It names pre-staging data into local memory as the remaining evasion and proposes an unpredictable, capacity-filling challenge to close it.",
            "response": null,
            "sources": [
              "S-0018"
            ],
            "helps": [
              {
                "by": "M-0014",
                "how": "Physical disconnection is proposed to exclude remote memory between the separated groups during a challenge. It depends on the isolation boundary being enforced."
              }
            ],
            "record": "M-0016",
            "represented_by": []
          },
          {
            "n": 3,
            "historical": false,
            "title": "Error rates not quantified",
            "classification": "open-question",
            "kind": "open-question",
            "severity": "minor",
            "status": "open",
            "evidence_scope": null,
            "scope_note": null,
            "related_finding": null,
            "description": "Monfared et al. show separable timing distributions. Their acceptance rule passes a GPU when its mean time per round stays at or below a chosen maximum, and an appendix outlines statistical tests for the proof-of-work puzzle. They leave hardware-specific threshold values to future work and report no false-positive or false-negative rates.",
            "response": null,
            "sources": [
              "S-0033"
            ],
            "record": "M-0016",
            "represented_by": []
          }
        ]
      }
    ],
    "scopeLimitations": [
      {
        "mech": "M-0016",
        "n": 1,
        "historical": false,
        "title": "Mismatches cannot be attributed to cheating or error",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "A failed hash or replay does not show whether it came from an evasion attempt, a random bit flip or an evaluation error. The author notes that if detected anomalies can plausibly be waved off as malfunctions, deterrence becomes less effective, so the parties need an agreed escalation procedure that ends in attribution.",
        "response": null,
        "sources": [
          "S-0018"
        ],
        "record": "I-0012"
      },
      {
        "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"
        ]
      }
    ],
    "openQuestions": [
      {
        "mech": "M-0016",
        "n": 3,
        "historical": false,
        "title": "Inspector agents may be manipulable",
        "classification": "open-question",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Automated compliance screening with LLM-based inspector agents must resist prompt-injection attacks. Adversarially trained systems might hide malicious actions with steganography, which makes backdoor detection an open problem.",
        "response": null,
        "sources": [
          "S-0018"
        ],
        "record": "I-0012"
      }
    ],
    "minor": 1,
    "minorFindings": [
      {
        "mech": "M-0016",
        "n": 2,
        "historical": false,
        "title": "Deliberate faults leak a bit each",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "minor",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "A malicious device can leak one bit by deliberately outputting a wrong result, which blocks a disclosure when the cross-comparison fails. The design therefore needs a pre-agreed budget of tolerated faults.",
        "response": null,
        "sources": [
          "S-0018"
        ],
        "record": "I-0012"
      }
    ],
    "minorBy": [
      {
        "id": "M-0016",
        "n": 1
      }
    ],
    "notDemonstrated": [
      "M-0016"
    ],
    "newChip": []
  },
  "findings": [
    {
      "mech": "M-0016",
      "record": "I-0012",
      "n": 1,
      "historical": false,
      "title": "Mismatches cannot be attributed to cheating or error",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "A failed hash or replay does not show whether it came from an evasion attempt, a random bit flip or an evaluation error. The author notes that if detected anomalies can plausibly be waved off as malfunctions, deterrence becomes less effective, so the parties need an agreed escalation procedure that ends in attribution.",
      "response": null,
      "sources": [
        "S-0018"
      ]
    },
    {
      "mech": "M-0016",
      "record": "I-0012",
      "n": 2,
      "historical": false,
      "title": "Deliberate faults leak a bit each",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "minor",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "A malicious device can leak one bit by deliberately outputting a wrong result, which blocks a disclosure when the cross-comparison fails. The design therefore needs a pre-agreed budget of tolerated faults.",
      "response": null,
      "sources": [
        "S-0018"
      ]
    },
    {
      "mech": "M-0016",
      "record": "I-0012",
      "n": 3,
      "historical": false,
      "title": "Inspector agents may be manipulable",
      "classification": "open-question",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Automated compliance screening with LLM-based inspector agents must resist prompt-injection attacks. Adversarially trained systems might hide malicious actions with steganography, which makes backdoor detection an open problem.",
      "response": null,
      "sources": [
        "S-0018"
      ]
    },
    {
      "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"
      ]
    }
  ],
  "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": "blocker",
          "mech": "M-0016",
          "text": "Exact replay needs complete hardware and software metadata, and the tolerable slowdown from emulation is an open question."
        }
      ]
    },
    {
      "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-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-0016",
          "text": "Tamper-evident, rapidly mass-manufacturable and retrofittable enclosures for side-channel defence are an open research question, and physical security against covert communication in every monitored data centre is challenging."
        }
      ]
    },
    {
      "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-0016",
          "text": "Empirical feasibility of passive optical splitting at 53–112 GBaud under realistic conditions is an open question."
        }
      ]
    },
    {
      "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-0016",
          "text": "A mass-manufacturable, good-enough side-channel defence, particularly power-line filtering, has not been constructed or red-teamed."
        }
      ]
    }
  ],
  "goal": null,
  "design": null,
  "dependencies": {
    "prerequisites": [
      {
        "id": "M-0013",
        "neededBy": [
          "M-0016"
        ]
      },
      {
        "id": "M-0002",
        "neededBy": [
          "M-0016"
        ]
      },
      {
        "id": "M-0008",
        "neededBy": [
          "M-0012"
        ]
      }
    ],
    "shared": [],
    "blockers": [
      {
        "mech": "M-0016",
        "n": 1,
        "historical": false,
        "text": "Empirical feasibility of passive optical splitting at 53–112 GBaud under realistic conditions is an open question.",
        "theme": "performance-compatibility",
        "blocked_by": "M-0013",
        "sources": [
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0016",
        "n": 2,
        "historical": false,
        "text": "Exact replay needs complete hardware and software metadata, and the tolerable slowdown from emulation is an open question.",
        "theme": "performance-compatibility",
        "blocked_by": "M-0002",
        "sources": [
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0016",
        "n": 3,
        "historical": false,
        "text": "Tamper-evident, rapidly mass-manufacturable and retrofittable enclosures for side-channel defence are an open research question, and physical security against covert communication in every monitored data centre is challenging.",
        "theme": "hardware-trust",
        "blocked_by": "M-0017",
        "sources": [
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0016",
        "n": 4,
        "historical": false,
        "text": "A mass-manufacturable, good-enough side-channel defence, particularly power-line filtering, has not been constructed or red-teamed.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0022",
        "sources": [
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0016",
        "n": 5,
        "historical": false,
        "text": "Distinguishing one server's DRAM contents from another's by challenge-response timing, and a general challenge-response protocol for diverse data types, are open.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0016",
        "sources": [
          "S-0018"
        ],
        "inProposal": true
      },
      {
        "mech": "M-0016",
        "n": 6,
        "historical": false,
        "text": "The threat model is under-developed and needs input from cybersecurity and AI threat-modelling experts.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-0018"
        ],
        "inProposal": null
      },
      {
        "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
      }
    ]
  },
  "exposure": {
    "weights": {
      "shown": [],
      "partial": [],
      "hidden": [
        "M-0012"
      ],
      "none": [],
      "unknown": [
        "M-0016"
      ]
    },
    "io": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [],
      "unknown": [
        "M-0016",
        "M-0012"
      ]
    },
    "training": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0012"
      ],
      "unknown": [
        "M-0016"
      ]
    }
  },
  "implementations": [
    {
      "mechanism": "M-0016",
      "selected": {
        "id": "I-0012",
        "title": "Low-trust AI compute verification system overview",
        "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
      },
      "implementations": [
        {
          "id": "I-0020",
          "title": "Data-centre memory challenging",
          "url": "https://trustbutveri.fyi/implementations/data-centre-memory-challenging/"
        },
        {
          "id": "I-0018",
          "title": "GPU contention probes",
          "url": "https://trustbutveri.fyi/implementations/gpu-contention-probes/"
        },
        {
          "id": "I-0012",
          "title": "Low-trust AI compute verification system overview",
          "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
        },
        {
          "id": "I-0021",
          "title": "SAGE",
          "url": "https://trustbutveri.fyi/implementations/sage-gpu-attestation/"
        },
        {
          "id": "I-0019",
          "title": "VRAM-residency challenge",
          "url": "https://trustbutveri.fyi/implementations/vram-residency-challenge/"
        }
      ]
    },
    {
      "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/"
        }
      ]
    }
  ],
  "sources": [
    {
      "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-1300",
      "title": "Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors",
      "authors": "N. Cankaya et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2606.10724",
      "path": "/sources/cankaya-fingerprinting-ai-cluster-io/"
    },
    {
      "id": "S-1308",
      "title": "On the Difficulty of Software-Based Attestation of Embedded Devices",
      "authors": "C. Castelluccia et al.",
      "year": 2009,
      "url": "https://s3.eurecom.fr/docs/ccs09_Castelluccia.pdf",
      "path": "/sources/castelluccia-difficulty-software-based-attestation/"
    },
    {
      "id": "S-0074",
      "title": "Refutation of \"On the Difficulty of Software-Based Attestation of Embedded Devices\"",
      "authors": "A. Perrig & L. van Doorn",
      "year": 2010,
      "url": "https://netsec.ethz.ch/publications/papers/perrig-ccs-refutation.pdf",
      "path": "/sources/perrig-refutation-software-based-attestation/"
    },
    {
      "id": "S-0033",
      "title": "Timing and Memory Telemetry on GPUs for AI Governance",
      "authors": "S. K. Monfared et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2602.09369",
      "path": "/sources/monfared-timing-memory-telemetry-gpus/"
    },
    {
      "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/"
    }
  ]
}