{
  "schema_version": "1.2",
  "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0018,M-0001&implementations=M-0001:I-0002",
  "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-0018",
      "title": "Chip location verification",
      "url": "https://trustbutveri.fyi/mechanisms/chip-location-verification/",
      "assessment_record": {
        "id": "M-0018",
        "title": "Chip location verification",
        "url": "https://trustbutveri.fyi/mechanisms/chip-location-verification/"
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R1",
        "scope": "bounding how far a chip is from trusted landmark servers when checked",
        "confidence": "medium",
        "evidence": [
          "S-1400",
          "S-1401",
          "S-3570",
          "S-1402",
          "S-1404",
          "S-1403",
          "S-0056"
        ]
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "existing-features",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "none",
        "io": "none",
        "training": "none",
        "note": "Times signed replies from chips; 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-0002",
        "title": "DiFR (Divergence From Reference)",
        "url": "https://trustbutveri.fyi/implementations/difr/"
      },
      "selected_implementation": {
        "id": "I-0002",
        "title": "DiFR (Divergence From Reference)",
        "url": "https://trustbutveri.fyi/implementations/difr/"
      },
      "readiness": {
        "level": "R2",
        "scope": "checking that outputs match the declared model, precision and sampling settings",
        "confidence": "medium",
        "evidence": [
          "S-0016",
          "S-0015",
          "S-1005",
          "S-1006",
          "S-1007",
          "S-1008",
          "S-1507",
          "S-3001"
        ]
      },
      "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": [],
    "adversarial": [
      "M-0018",
      "M-0001"
    ],
    "noNewHardware": [
      "M-0018",
      "M-0001"
    ],
    "mitigated": [],
    "notCounted": []
  },
  "properties": {
    "covered": [],
    "production": [],
    "adversarial": [
      "M-0018",
      "M-0001"
    ],
    "noNewHardware": [
      "M-0018",
      "M-0001"
    ],
    "mitigated": [],
    "notCounted": []
  },
  "attack_testing": [
    {
      "id": "M-0018",
      "record": "M-0018",
      "evaluation": "analysis",
      "in_setting": true
    },
    {
      "id": "M-0001",
      "record": "I-0002",
      "evaluation": "analysis",
      "in_setting": true
    }
  ],
  "selected_implementations": {
    "M-0001": "I-0002"
  },
  "weaknesses": {
    "gaps": [],
    "excluded": [],
    "unlinked": [],
    "critical": [],
    "significant": [
      {
        "mech": "M-0018",
        "n": 1,
        "title": "Extracting a chip's key lets another device answer for it",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Ping-based protocols rely on cryptographic keys stored on the chip. Tee and Happel argue that an adversary with physical access could extract these keys and so compromise location verification. They propose GPU fingerprints as a mitigation, so far tested on 24 GPUs. Brass and Aarne assume the keys are stored securely, for example in a TPM.",
        "response": null,
        "sources": [
          "S-1403",
          "S-1400"
        ]
      },
      {
        "mech": "M-0018",
        "n": 2,
        "title": "Added delay can shift an estimated position",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Brass and Aarne cite internet-geolocation research in which artificially increased round-trip times moved the estimated location by up to 1,000 km, with a 74% chance of avoiding detection. Avellar and Grunewald list inflated ping times from circuitous routing as an evasion route. Added delay only loosens a distance bound, and Brass and Aarne propose a hard time limit as the counter: a chip that replies too slowly cannot be ruled out of a restricted location.",
        "response": null,
        "sources": [
          "S-1400",
          "S-1402"
        ]
      },
      {
        "mech": "M-0018",
        "n": 3,
        "title": "Faster-than-assumed network paths",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Brass and Aarne list dark fibre and other private high-speed interconnects as ways to lower measured delays artificially. They judge that leasing dark fibre would probably not be a considerable challenge for covertly or openly adversarial actors. Avellar and Grunewald note that this can make a chip appear to be somewhere else entirely. A limit set at the vacuum speed of light cannot be beaten, but it makes honest chips fail more often.",
        "response": null,
        "sources": [
          "S-1400",
          "S-1402"
        ]
      },
      {
        "mech": "M-0018",
        "n": 4,
        "title": "Compromised landmarks can falsify measurements",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "A party that controls landmark servers can report false timing. Brass and Aarne cite research in which manipulating a third of the landmarks shifted the estimated location by about 700 km. Avellar and Grunewald note that compromised landmarks let adversaries spoof travel-time measurements directly. The draft specification asks verifiers to require anchors in diverse places, run by several independent operators.",
        "response": null,
        "sources": [
          "S-1400",
          "S-1402",
          "S-1404"
        ]
      },
      {
        "mech": "M-0001",
        "n": 1,
        "title": "Statistical tolerance leaves a covert channel",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Statistical schemes can put an upper bound on an adversary's covert bandwidth, but cannot close it. In the companion exfiltration study, the detector cut exfiltratable information to under 0.5% under benign prompt traffic. It did not cut it to zero. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study attacked that detector, which uses the same Gumbel-margin statistic. An adversary who controls the prompts roughly doubled the bits leaked per token. Across six models, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target DiFR's check that outputs match the declared configuration.",
        "response": null,
        "sources": [
          "S-0020",
          "S-0015",
          "S-1507"
        ],
        "record": "I-0002"
      },
      {
        "mech": "M-0001",
        "n": 3,
        "title": "Speculative decoding and multi-model sampling not evaluated",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The algorithms and experiments cover sampling from a single LLM. Speculative decoding was not evaluated. The authors sketch an extension to one speculative-decoding algorithm, without experiments. They note that other variants would need modified verification and extra metadata.",
        "response": null,
        "sources": [
          "S-0016"
        ],
        "record": "I-0002"
      }
    ],
    "criticalMechanisms": [],
    "significantMechanisms": [
      "M-0018",
      "M-0001"
    ],
    "familyContext": [
      {
        "id": "M-0001",
        "implementation": "I-0002",
        "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": 1,
    "minorFindings": [
      {
        "mech": "M-0001",
        "n": 2,
        "title": "Mixed hardware widens the honest baseline",
        "kind": "open-question",
        "severity": "minor",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "For Qwen3-30B-A3B, pooling honest runs across A100 and H200 GPUs and parallelism setups broadened the honest score distribution. Token-DiFR then failed 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 did. The authors report that matched provider and verifier environments, or pooling that weights rare large deviations, restore detection.",
        "response": null,
        "sources": [
          "S-0016"
        ],
        "record": "I-0002"
      }
    ],
    "minorBy": [
      {
        "id": "M-0001",
        "n": 1
      }
    ],
    "notDemonstrated": [
      "M-0018"
    ],
    "newChip": []
  },
  "findings": [
    {
      "mech": "M-0018",
      "record": "M-0018",
      "n": 1,
      "title": "Extracting a chip's key lets another device answer for it",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Ping-based protocols rely on cryptographic keys stored on the chip. Tee and Happel argue that an adversary with physical access could extract these keys and so compromise location verification. They propose GPU fingerprints as a mitigation, so far tested on 24 GPUs. Brass and Aarne assume the keys are stored securely, for example in a TPM.",
      "response": null,
      "sources": [
        "S-1403",
        "S-1400"
      ]
    },
    {
      "mech": "M-0018",
      "record": "M-0018",
      "n": 2,
      "title": "Added delay can shift an estimated position",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Brass and Aarne cite internet-geolocation research in which artificially increased round-trip times moved the estimated location by up to 1,000 km, with a 74% chance of avoiding detection. Avellar and Grunewald list inflated ping times from circuitous routing as an evasion route. Added delay only loosens a distance bound, and Brass and Aarne propose a hard time limit as the counter: a chip that replies too slowly cannot be ruled out of a restricted location.",
      "response": null,
      "sources": [
        "S-1400",
        "S-1402"
      ]
    },
    {
      "mech": "M-0018",
      "record": "M-0018",
      "n": 3,
      "title": "Faster-than-assumed network paths",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Brass and Aarne list dark fibre and other private high-speed interconnects as ways to lower measured delays artificially. They judge that leasing dark fibre would probably not be a considerable challenge for covertly or openly adversarial actors. Avellar and Grunewald note that this can make a chip appear to be somewhere else entirely. A limit set at the vacuum speed of light cannot be beaten, but it makes honest chips fail more often.",
      "response": null,
      "sources": [
        "S-1400",
        "S-1402"
      ]
    },
    {
      "mech": "M-0018",
      "record": "M-0018",
      "n": 4,
      "title": "Compromised landmarks can falsify measurements",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "A party that controls landmark servers can report false timing. Brass and Aarne cite research in which manipulating a third of the landmarks shifted the estimated location by about 700 km. Avellar and Grunewald note that compromised landmarks let adversaries spoof travel-time measurements directly. The draft specification asks verifiers to require anchors in diverse places, run by several independent operators.",
      "response": null,
      "sources": [
        "S-1400",
        "S-1402",
        "S-1404"
      ]
    },
    {
      "mech": "M-0001",
      "record": "I-0002",
      "n": 1,
      "title": "Statistical tolerance leaves a covert channel",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Statistical schemes can put an upper bound on an adversary's covert bandwidth, but cannot close it. In the companion exfiltration study, the detector cut exfiltratable information to under 0.5% under benign prompt traffic. It did not cut it to zero. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study attacked that detector, which uses the same Gumbel-margin statistic. An adversary who controls the prompts roughly doubled the bits leaked per token. Across six models, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target DiFR's check that outputs match the declared configuration.",
      "response": null,
      "sources": [
        "S-0020",
        "S-0015",
        "S-1507"
      ]
    },
    {
      "mech": "M-0001",
      "record": "I-0002",
      "n": 2,
      "title": "Mixed hardware widens the honest baseline",
      "kind": "open-question",
      "severity": "minor",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "For Qwen3-30B-A3B, pooling honest runs across A100 and H200 GPUs and parallelism setups broadened the honest score distribution. Token-DiFR then failed 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 did. The authors report that matched provider and verifier environments, or pooling that weights rare large deviations, restore detection.",
      "response": null,
      "sources": [
        "S-0016"
      ]
    },
    {
      "mech": "M-0001",
      "record": "I-0002",
      "n": 3,
      "title": "Speculative decoding and multi-model sampling not evaluated",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The algorithms and experiments cover sampling from a single LLM. Speculative decoding was not evaluated. The authors sketch an extension to one speculative-decoding algorithm, without experiments. They note that other variants would need modified verification and extra metadata.",
      "response": null,
      "sources": [
        "S-0016"
      ]
    }
  ],
  "possible_additions": [
    {
      "id": "M-0008",
      "title": "TEE remote attestation for AI workloads",
      "url": "https://trustbutveri.fyi/mechanisms/tee-remote-attestation/",
      "readiness": "R3",
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "prerequisite",
          "mech": "M-0018"
        }
      ]
    }
  ],
  "goal": null,
  "design": null,
  "dependencies": {
    "prerequisites": [
      {
        "id": "M-0008",
        "neededBy": [
          "M-0018"
        ]
      }
    ],
    "shared": [],
    "blockers": [
      {
        "mech": "M-0018",
        "n": 1,
        "text": "No public code or reproducible end-to-end location results are available for the reported H100 prototype.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-1401",
          "S-3570"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0018",
        "n": 2,
        "text": "Per-chip keys must be provisioned and protected against extraction; hardware-integrated, tamper-resistant versions still need R&D.",
        "theme": "hardware-trust",
        "blocked_by": null,
        "sources": [
          "S-1400",
          "S-1403",
          "S-0007"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0018",
        "n": 3,
        "text": "The time limit forces a trade-off: a limit at the speed of light in fibre can be beaten by faster links, while one at the vacuum speed of light makes honest chips fail often.",
        "theme": "protocol-soundness",
        "blocked_by": null,
        "sources": [
          "S-1400"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0018",
        "n": 4,
        "text": "A trusted landmark network must be built and secured, and who should operate it, under what oversight, is unsettled.",
        "theme": "access-governance",
        "blocked_by": null,
        "sources": [
          "S-1400",
          "S-1402"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 1,
        "text": "The verifier needs the model weights, so outsiders cannot use the method to verify providers of closed-weights models.",
        "theme": "privacy-leakage",
        "blocked_by": null,
        "sources": [
          "S-0016"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 2,
        "text": "The verifier must know and match the provider's sampling procedure, and in one prototype a sampling mismatch in a newer vLLM version produced large spurious logit differences.",
        "theme": "performance-compatibility",
        "blocked_by": null,
        "sources": [
          "S-0016",
          "S-1006"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0001",
        "n": 3,
        "text": "No independent red-team of DiFR's consistency check has been published, Amodo rates recomputation red-teaming 'not started', and the one independent attack study targets an exfiltration detector built on the same statistic.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-1008",
          "S-1507"
        ],
        "inProposal": null
      }
    ]
  },
  "exposure": {
    "weights": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0018"
      ],
      "unknown": [
        "M-0001"
      ]
    },
    "io": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0018"
      ],
      "unknown": [
        "M-0001"
      ]
    },
    "training": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0018"
      ],
      "unknown": [
        "M-0001"
      ]
    }
  },
  "implementations": [
    {
      "mechanism": "M-0018",
      "selected": null,
      "implementations": [
        {
          "id": "I-0009",
          "title": "Lucid sovereignty (location) certificates",
          "url": "https://trustbutveri.fyi/implementations/lucid-location-certificates/"
        }
      ]
    },
    {
      "mechanism": "M-0001",
      "selected": {
        "id": "I-0002",
        "title": "DiFR (Divergence From Reference)",
        "url": "https://trustbutveri.fyi/implementations/difr/"
      },
      "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-1400",
      "title": "Location Verification for AI Chips",
      "authors": "A. Brass & O. Aarne",
      "year": 2024,
      "url": "https://www.iaps.ai/research/location-verification-for-ai-chips",
      "path": "/sources/brass-location-verification-ai-chips/"
    },
    {
      "id": "S-1401",
      "title": "Location Verification for AI Chips (issue brief)",
      "authors": "A. Brass",
      "year": 2025,
      "url": "https://static1.squarespace.com/static/64edf8e7f2b10d716b5ba0e1/t/6827b67275666f3757f134ea/1747433075281/Location+Verification+two-pager.pdf",
      "path": "/sources/brass-location-verification-issue-brief/"
    },
    {
      "id": "S-3570",
      "title": "Ping-based Location",
      "authors": "Ulyssean",
      "year": 2025,
      "url": "https://ping-location.info/",
      "path": "/sources/ulyssean-ping-based-location-demo/"
    },
    {
      "id": "S-1402",
      "title": "Near-Term Verification Methods for AI Chip Exports",
      "authors": "B. Avellar & E. Grunewald",
      "year": 2026,
      "url": "https://www.iaps.ai/research/near-term-verification-methods-for-ai-chip-exports",
      "path": "/sources/avellar-near-term-verification-ai-chip-exports/"
    },
    {
      "id": "S-1404",
      "title": "Sovereignty Certificates: draft specification, version 0.1.0",
      "authors": "Sovereignty Certificates Working Group",
      "year": 2025,
      "url": "https://github.com/Lucid-Computing/sovereignty-certificate-specification",
      "path": "/sources/sovereignty-certificates-specification/"
    },
    {
      "id": "S-1403",
      "title": "GPU Fingerprinting for Location Verification",
      "authors": "W. Tee & J. Happel",
      "year": 2026,
      "url": "https://arxiv.org/abs/2605.01930",
      "path": "/sources/tee-gpu-fingerprinting-location-verification/"
    },
    {
      "id": "S-0056",
      "title": "Secure, Governable Chips: Using On-Chip Mechanisms to Manage National Security Risks from AI & Advanced Computing",
      "authors": "O. Aarne et al.",
      "year": 2024,
      "url": "https://www.cnas.org/publications/reports/secure-governable-chips",
      "path": "/sources/aarne-secure-governable-chips/"
    },
    {
      "id": "S-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-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-1005",
      "title": "adamkarvonen/difr (GitHub repository)",
      "authors": "A. Karvonen",
      "year": 2025,
      "url": "https://github.com/adamkarvonen/difr",
      "path": "/sources/karvonen-difr-code/"
    },
    {
      "id": "S-1006",
      "title": "Scaling Recomputation Inference Verification",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/notes/2026-09-02-scaling-recomputation-inference-verification/",
      "path": "/sources/amodo-scaling-recomputation-inference-verification/"
    },
    {
      "id": "S-1007",
      "title": "Amodo-Design/Inference-Recomputation-Prototype (GitHub repository)",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://github.com/Amodo-Design/Inference-Recomputation-Prototype",
      "path": "/sources/amodo-inference-recomputation-prototype-code/"
    },
    {
      "id": "S-1008",
      "title": "AI 2040 Plan A — Verification SITREP",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/ai-verification/plan-a-sitrep/",
      "path": "/sources/amodo-plan-a-verification-sitrep/"
    },
    {
      "id": "S-1507",
      "title": "Adversarial Entropy Inflation Against Gumbel-Based Inference Verification",
      "authors": "N. Kezins",
      "year": 2026,
      "url": "https://arxiv.org/abs/2608.23375",
      "path": "/sources/kezins-adversarial-entropy-inflation/"
    },
    {
      "id": "S-3001",
      "title": "An Inference Verification Prototype — Stage 1",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/notes/2026-06-29-inference-verification-prototype/",
      "path": "/sources/amodo-inference-verification-prototype-stage-1/"
    },
    {
      "id": "S-0020",
      "title": "Bit-Exact AI Inference Verification Without Performance Tradeoffs",
      "authors": "N. Cankaya",
      "year": 2026,
      "url": "https://arxiv.org/abs/2606.00279",
      "path": "/sources/cankaya-bit-exact-inference-verification/"
    },
    {
      "id": "S-0017",
      "title": "Example Schemes for Verifying High-Stakes AI Agreements",
      "authors": "Amodo Design",
      "year": 2026,
      "url": "https://amododesign.com/notes/2026-06-23-verification-algorithms/",
      "path": "/sources/amodo-example-schemes-high-stakes-ai-agreements/"
    },
    {
      "id": "S-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-0007",
      "title": "Hardware-Level Governance of AI Compute: A Feasibility Taxonomy for Regulatory Compliance and Treaty Verification",
      "authors": "S. Ansari",
      "year": 2026,
      "url": "https://arxiv.org/abs/2604.04712",
      "path": "/sources/ansari-hardware-level-governance-ai-compute/"
    }
  ]
}