{
  "schema_version": "1.2",
  "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0017,M-0001&implementations=M-0001:I-0001",
  "data_generated": "2026-10-08",
  "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 readiness",
        "question": "How mature must each mechanism be?",
        "options": [
          {
            "value": "R1",
            "label": "R1 Proposed"
          },
          {
            "value": "R2",
            "label": "R2 Demonstrated"
          },
          {
            "value": "R3",
            "label": "R3 In production"
          },
          {
            "value": "R4",
            "label": "R4 Deployment-ready"
          }
        ],
        "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_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 findings on the assessed records; open_critical_context names conditional family findings 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-0017",
      "title": "Tamper evidence for verifier devices",
      "url": "https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/",
      "assessment_record": {
        "id": "M-0017",
        "title": "Tamper evidence for verifier devices",
        "url": "https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/"
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R2",
        "scope": "detecting probing of proposed verifier hardware, using server and electronics prototypes as evidence",
        "confidence": "medium",
        "evidence": [
          "S-0052",
          "S-1315",
          "S-0051",
          "S-0050",
          "S-3262",
          "S-1316",
          "S-0018"
        ]
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "retrofit-device",
        "prover_cooperation": "partial",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "none",
        "io": "none",
        "training": "none",
        "note": "Protects verifier devices; it does not handle model data."
      },
      "family_finding_context": [],
      "filter_issues": []
    },
    {
      "id": "M-0001",
      "title": "Sampled inference recomputation",
      "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/",
      "assessment_record": {
        "id": "I-0001",
        "title": "TOPLOC",
        "url": "https://trustbutveri.fyi/implementations/toploc/"
      },
      "selected_implementation": {
        "id": "I-0001",
        "title": "TOPLOC",
        "url": "https://trustbutveri.fyi/implementations/toploc/"
      },
      "readiness": {
        "level": "R3",
        "scope": "checking that untrusted providers used the claimed model, prompt and precision",
        "confidence": "low",
        "evidence": [
          "S-1000",
          "S-1001",
          "S-1003",
          "S-1004",
          "S-3000"
        ]
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "none",
        "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,
          "title": "Tolerance for numerical noise leaves a covert channel",
          "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."
            }
          ],
          "record": "M-0001",
          "represented_by": []
        },
        {
          "n": 2,
          "title": "Only recorded traffic is checked",
          "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."
            }
          ],
          "record": "M-0001",
          "represented_by": []
        },
        {
          "n": 3,
          "title": "Some inference optimizations are not covered",
          "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"
          ],
          "record": "M-0001",
          "represented_by": []
        },
        {
          "n": 4,
          "title": "Mixed hardware widens the honest baseline",
          "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"
          ],
          "record": "M-0001",
          "represented_by": []
        }
      ],
      "filter_issues": []
    }
  ],
  "strengths": {
    "covered": [],
    "production": [
      "M-0001"
    ],
    "adversarial": [
      "M-0017",
      "M-0001"
    ],
    "noNewHardware": [
      "M-0001"
    ],
    "mitigated": [],
    "notCounted": []
  },
  "properties": {
    "covered": [],
    "production": [
      "M-0001"
    ],
    "adversarial": [
      "M-0017",
      "M-0001"
    ],
    "noNewHardware": [
      "M-0001"
    ],
    "mitigated": [],
    "notCounted": []
  },
  "attack_testing": [
    {
      "id": "M-0017",
      "record": "M-0017",
      "evaluation": "analysis",
      "in_setting": true
    },
    {
      "id": "M-0001",
      "record": "I-0001",
      "evaluation": "analysis",
      "in_setting": true
    }
  ],
  "selected_implementations": {
    "M-0001": "I-0001"
  },
  "weaknesses": {
    "gaps": [],
    "excluded": [],
    "unlinked": [],
    "critical": [],
    "significant": [
      {
        "mech": "M-0017",
        "n": 1,
        "title": "Seals are often defeated with simple methods",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": "mechanism",
        "scope_note": "Published defeats of general security seals. They warn about proposed verifier-device seals, but do not demonstrate defeat of an AI verification enclosure or sensor.",
        "related_finding": null,
        "description": "In 1996 a Los Alamos vulnerability assessment defeated all 94 security seals it examined, with 132 defeats in total, using rapid, inexpensive, low-tech methods. It found that seal cost did not predict security. In 2001 Johnston reported that high-tech seals are often easier to defeat than low-tech ones.",
        "response": null,
        "sources": [
          "S-1317",
          "S-1318"
        ]
      },
      {
        "mech": "M-0017",
        "n": 2,
        "title": "Security depends on inspection protocols",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": "mechanism",
        "scope_note": "An inspection and protocol requirement drawn from safeguards and enclosure studies, not a reported break of a deployed AI verifier.",
        "related_finding": null,
        "description": "Johnston argues that a seal is no better than the protocols for using it, and that inspectors are usually given little useful information on how to detect tampering. The Sandia survey notes that larger enclosures are hard to inspect fully and that sensor data must be authenticated.",
        "response": null,
        "sources": [
          "S-1318",
          "S-1316"
        ]
      },
      {
        "mech": "M-0017",
        "n": 3,
        "title": "Attack classes outside published models",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": "mechanism",
        "scope_note": "The radio compensation result is emulated using measured channel data under a known-reference attacker model. It is not a physical bypass demonstration against an AI verifier enclosure.",
        "related_finding": null,
        "description": "The authors of the batteryless cover say they cannot assess chemical-solvent attacks, which exceed their expertise, and deem cover removal impractical. Anti-Tamper Radio's reference can drift as the environment or measurement system ages; the authors suggest gradually renewing the reference. A 2025 follow-up by some of the same authors shows, by emulation on measured channel data, that an attacker who knows the reference channel and the needle's effect on it could inject a signal that cancels the change caused by a needle insertion. It proposes a reconfigurable intelligent surface that randomizes the channel as a countermeasure.",
        "response": null,
        "sources": [
          "S-1315",
          "S-0052",
          "S-3261"
        ]
      },
      {
        "mech": "M-0001",
        "n": 1,
        "title": "Speculative decoding goes undetected",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The TOPLOC authors state that it cannot detect speculative decoding. In speculative decoding, a provider decodes with a cheaper model and uses the larger model only for prefill.",
        "response": null,
        "sources": [
          "S-1000"
        ],
        "record": "I-0001"
      },
      {
        "mech": "M-0001",
        "n": 2,
        "title": "Last-layer activations could be spoofed",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The TOPLOC authors name spoofing of the last hidden layer's activations as a potential attack. A provider could do this by pruning intermediate layers or by using a smaller model.",
        "response": null,
        "sources": [
          "S-1000"
        ],
        "record": "I-0001"
      },
      {
        "mech": "M-0001",
        "n": 3,
        "title": "Subtle modifications are harder to detect",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The TOPLOC authors state that large changes to the model or prompt are straightforward to detect, but subtle modifications are harder. In preliminary experiments, the margin separating fp8 from bf16 generation was small. The authors did not test whether TOPLOC distinguishes types of KV-cache compression.",
        "response": null,
        "sources": [
          "S-1000"
        ],
        "record": "I-0001"
      },
      {
        "mech": "M-0001",
        "n": 4,
        "title": "Tolerance leaves covert bandwidth",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "TOPLOC accepts approximate matches. A check of this kind can put an upper bound on the covert bandwidth available to an adversary, but it cannot close that bandwidth. The limit applies to all statistical verification schemes.",
        "response": null,
        "sources": [
          "S-0020"
        ],
        "record": "I-0001"
      }
    ],
    "criticalMechanisms": [],
    "significantMechanisms": [
      "M-0017",
      "M-0001"
    ],
    "familyContext": [
      {
        "id": "M-0001",
        "implementation": "I-0001",
        "flaws": [
          {
            "n": 1,
            "title": "Tolerance for numerical noise leaves a covert channel",
            "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."
              }
            ],
            "record": "M-0001",
            "represented_by": []
          },
          {
            "n": 2,
            "title": "Only recorded traffic is checked",
            "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."
              }
            ],
            "record": "M-0001",
            "represented_by": []
          },
          {
            "n": 3,
            "title": "Some inference optimizations are not covered",
            "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"
            ],
            "record": "M-0001",
            "represented_by": []
          },
          {
            "n": 4,
            "title": "Mixed hardware widens the honest baseline",
            "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"
            ],
            "record": "M-0001",
            "represented_by": []
          }
        ]
      }
    ],
    "minor": 0,
    "minorFindings": [],
    "minorBy": [],
    "notDemonstrated": [],
    "newChip": []
  },
  "findings": [
    {
      "mech": "M-0017",
      "record": "M-0017",
      "n": 1,
      "title": "Seals are often defeated with simple methods",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": "mechanism",
      "scope_note": "Published defeats of general security seals. They warn about proposed verifier-device seals, but do not demonstrate defeat of an AI verification enclosure or sensor.",
      "related_finding": null,
      "description": "In 1996 a Los Alamos vulnerability assessment defeated all 94 security seals it examined, with 132 defeats in total, using rapid, inexpensive, low-tech methods. It found that seal cost did not predict security. In 2001 Johnston reported that high-tech seals are often easier to defeat than low-tech ones.",
      "response": null,
      "sources": [
        "S-1317",
        "S-1318"
      ]
    },
    {
      "mech": "M-0017",
      "record": "M-0017",
      "n": 2,
      "title": "Security depends on inspection protocols",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": "mechanism",
      "scope_note": "An inspection and protocol requirement drawn from safeguards and enclosure studies, not a reported break of a deployed AI verifier.",
      "related_finding": null,
      "description": "Johnston argues that a seal is no better than the protocols for using it, and that inspectors are usually given little useful information on how to detect tampering. The Sandia survey notes that larger enclosures are hard to inspect fully and that sensor data must be authenticated.",
      "response": null,
      "sources": [
        "S-1318",
        "S-1316"
      ]
    },
    {
      "mech": "M-0017",
      "record": "M-0017",
      "n": 3,
      "title": "Attack classes outside published models",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": "mechanism",
      "scope_note": "The radio compensation result is emulated using measured channel data under a known-reference attacker model. It is not a physical bypass demonstration against an AI verifier enclosure.",
      "related_finding": null,
      "description": "The authors of the batteryless cover say they cannot assess chemical-solvent attacks, which exceed their expertise, and deem cover removal impractical. Anti-Tamper Radio's reference can drift as the environment or measurement system ages; the authors suggest gradually renewing the reference. A 2025 follow-up by some of the same authors shows, by emulation on measured channel data, that an attacker who knows the reference channel and the needle's effect on it could inject a signal that cancels the change caused by a needle insertion. It proposes a reconfigurable intelligent surface that randomizes the channel as a countermeasure.",
      "response": null,
      "sources": [
        "S-1315",
        "S-0052",
        "S-3261"
      ]
    },
    {
      "mech": "M-0001",
      "record": "I-0001",
      "n": 1,
      "title": "Speculative decoding goes undetected",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The TOPLOC authors state that it cannot detect speculative decoding. In speculative decoding, a provider decodes with a cheaper model and uses the larger model only for prefill.",
      "response": null,
      "sources": [
        "S-1000"
      ]
    },
    {
      "mech": "M-0001",
      "record": "I-0001",
      "n": 2,
      "title": "Last-layer activations could be spoofed",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The TOPLOC authors name spoofing of the last hidden layer's activations as a potential attack. A provider could do this by pruning intermediate layers or by using a smaller model.",
      "response": null,
      "sources": [
        "S-1000"
      ]
    },
    {
      "mech": "M-0001",
      "record": "I-0001",
      "n": 3,
      "title": "Subtle modifications are harder to detect",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The TOPLOC authors state that large changes to the model or prompt are straightforward to detect, but subtle modifications are harder. In preliminary experiments, the margin separating fp8 from bf16 generation was small. The authors did not test whether TOPLOC distinguishes types of KV-cache compression.",
      "response": null,
      "sources": [
        "S-1000"
      ]
    },
    {
      "mech": "M-0001",
      "record": "I-0001",
      "n": 4,
      "title": "Tolerance leaves covert bandwidth",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "TOPLOC accepts approximate matches. A check of this kind can put an upper bound on the covert bandwidth available to an adversary, but it cannot close that bandwidth. The limit applies to all statistical verification schemes.",
      "response": null,
      "sources": [
        "S-0020"
      ]
    }
  ],
  "possible_additions": [],
  "goal": null,
  "design": null,
  "dependencies": {
    "prerequisites": [],
    "shared": [],
    "blockers": [
      {
        "mech": "M-0017",
        "n": 1,
        "text": "No tamper-evident enclosure has been designed for AI verifier hardware at retrofit scale.",
        "theme": "hardware-trust",
        "blocked_by": null,
        "sources": [
          "S-0018"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0017",
        "n": 2,
        "text": "Battery-backed designs add bulk, limit operating temperature (+10 °C to +35 °C for the IBM 4765) and complicate transport.",
        "theme": "performance-compatibility",
        "blocked_by": null,
        "sources": [
          "S-1315"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0017",
        "n": 3,
        "text": "Active monitoring needs power, and visual inspection of large enclosures faces access limits.",
        "theme": "access-governance",
        "blocked_by": null,
        "sources": [
          "S-1316"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0017",
        "n": 4,
        "text": "No evaluation has been published in the AI verification setting.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-0018"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 1,
        "text": "No independent security evaluation has been published, and Amodo Design rates red-teaming of recomputation schemes as 'not started'.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-1008"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 2,
        "text": "The verifier must run the model itself, which suits the paper's setting of providers serving open-weights models.",
        "theme": "privacy-leakage",
        "blocked_by": null,
        "sources": [
          "S-1000"
        ],
        "inProposal": null
      }
    ]
  },
  "exposure": {
    "weights": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0017"
      ],
      "unknown": [
        "M-0001"
      ]
    },
    "io": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0017"
      ],
      "unknown": [
        "M-0001"
      ]
    },
    "training": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0017"
      ],
      "unknown": [
        "M-0001"
      ]
    }
  },
  "implementations": [
    {
      "mechanism": "M-0017",
      "selected": null,
      "implementations": [
        {
          "id": "I-0011",
          "title": "AI 2040 inference-only verification stack",
          "url": "https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/"
        }
      ]
    },
    {
      "mechanism": "M-0001",
      "selected": {
        "id": "I-0001",
        "title": "TOPLOC",
        "url": "https://trustbutveri.fyi/implementations/toploc/"
      },
      "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-0052",
      "title": "Anti-Tamper Radio: System-Level Tamper Detection for Computing Systems",
      "authors": "P. Staat et al.",
      "year": 2022,
      "url": "https://ieeexplore.ieee.org/document/9833631/",
      "path": "/sources/staat-anti-tamper-radio/"
    },
    {
      "id": "S-1315",
      "title": "Secure Physical Enclosures from Covers with Tamper-Resistance",
      "authors": "V. Immler et al.",
      "year": 2019,
      "url": "https://tches.iacr.org/index.php/TCHES/article/view/7334",
      "path": "/sources/immler-secure-physical-enclosures-covers/"
    },
    {
      "id": "S-0051",
      "title": "ImpedanceVerif: On-Chip Impedance Sensing for System-Level Tampering Detection",
      "authors": "T. Mosavirik et al.",
      "year": 2023,
      "url": "https://eprint.iacr.org/2022/946",
      "path": "/sources/mosavirik-impedanceverif/"
    },
    {
      "id": "S-0050",
      "title": "IBM 4765 Cryptographic Coprocessor Security Module: Security Policy",
      "authors": "IBM Corporation",
      "year": 2012,
      "url": "https://csrc.nist.gov/csrc/media/projects/cryptographic-module-validation-program/documents/security-policies/140sp1505.pdf",
      "path": "/sources/ibm-4765-security-policy/"
    },
    {
      "id": "S-3262",
      "title": "PHYSEC SEAL: Change detection for maximum safety",
      "authors": "PHYSEC GmbH",
      "year": 2026,
      "url": "https://www.physec.de/en/solutions/physec-seal/",
      "path": "/sources/physec-seal/"
    },
    {
      "id": "S-1316",
      "title": "Tamper-Indicating Enclosures, A Current Survey",
      "authors": "H. A. Smartt & Z. N. Gastelum",
      "year": 2015,
      "url": "https://www.osti.gov/servlets/purl/1256541",
      "path": "/sources/smartt-tamper-indicating-enclosures-survey/"
    },
    {
      "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-1317",
      "title": "Physical Security and Tamper-Indicating Devices",
      "authors": "R. G. Johnston & A. R. E. Garcia",
      "year": 1996,
      "url": "https://www.osti.gov/servlets/purl/459707",
      "path": "/sources/johnston-physical-security-tamper-indicating-devices/"
    },
    {
      "id": "S-1318",
      "title": "Tamper Detection for Safeguards and Treaty Monitoring: Fantasies, Realities, and Potentials",
      "authors": "R. G. Johnston",
      "year": 2001,
      "url": "https://www.nonproliferation.org/wp-content/uploads/npr/81john.pdf",
      "path": "/sources/johnston-tamper-detection-safeguards-treaty-monitoring/"
    },
    {
      "id": "S-3261",
      "title": "Anti-Tamper Radio Meets Reconfigurable Intelligent Surface for System-Level Tamper Detection",
      "authors": "M. S. Tabar et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2503.14279",
      "path": "/sources/tabar-anti-tamper-radio-ris/"
    },
    {
      "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-1004",
      "title": "SYNTHETIC-2",
      "authors": "Prime Intellect",
      "year": 2025,
      "url": "https://www.primeintellect.ai/blog/synthetic-2",
      "path": "/sources/primeintellect-synthetic-2/"
    },
    {
      "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-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-0015",
      "title": "Verifying LLM Inference to Detect Model Weight Exfiltration",
      "authors": "R. Rinberg et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2511.02620",
      "path": "/sources/rinberg-verifying-llm-inference-weight-exfiltration/"
    },
    {
      "id": "S-1507",
      "title": "Adversarial Entropy Inflation Against Gumbel-Based Inference Verification",
      "authors": "N. Kezins",
      "year": 2026,
      "url": "https://arxiv.org/abs/2608.23375",
      "path": "/sources/kezins-adversarial-entropy-inflation/"
    },
    {
      "id": "S-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-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-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/"
    }
  ]
}