{
  "schema_version": "1.2",
  "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0024&tested=red-teamed",
  "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": "red-teamed",
    "hide": []
  },
  "mechanisms_passing_filters": 7,
  "claims": [],
  "mechanisms": [
    {
      "id": "M-0024",
      "title": "Bounding unexplained information in outputs",
      "url": "https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/",
      "assessment_record": {
        "id": "M-0024",
        "title": "Bounding unexplained information in outputs",
        "url": "https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/"
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R2",
        "scope": "bounding how much hidden information can leave in checked inference outputs",
        "confidence": "low",
        "evidence": [
          "S-0019",
          "S-0015",
          "S-1507"
        ]
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "retrofit-device",
        "prover_cooperation": "required",
        "adversarial_evaluation": "independent-red-team"
      },
      "claims": [],
      "exposure": {
        "weights": "partial",
        "io": "partial",
        "training": "none",
        "note": "Depends on where recomputation runs: in a sealed enclosure, or with zero-knowledge proofs, the verifier need not see the weights or the traffic."
      },
      "family_finding_context": [],
      "filter_issues": []
    }
  ],
  "strengths": {
    "covered": [],
    "production": [],
    "adversarial": [
      "M-0024"
    ],
    "noNewHardware": [],
    "mitigated": [],
    "notCounted": []
  },
  "properties": {
    "covered": [],
    "production": [],
    "adversarial": [
      "M-0024"
    ],
    "noNewHardware": [],
    "mitigated": [],
    "notCounted": []
  },
  "attack_testing": [
    {
      "id": "M-0024",
      "record": "M-0024",
      "evaluation": "independent-red-team",
      "in_setting": true
    }
  ],
  "selected_implementations": {},
  "weaknesses": {
    "gaps": [],
    "excluded": [],
    "unlinked": [],
    "critical": [],
    "significant": [
      {
        "mech": "M-0024",
        "n": 1,
        "title": "Prompt-controlled entropy inflation widens the covert channel",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Gumbel-based inference verification tolerates token choices that honest GPU nondeterminism could produce, and the size of that tolerated set grows with the model's output entropy. Kezins, an independent researcher, showed that an adversary who controls the prompt distribution can raise output entropy and roughly double the bits leaked per token. Across six models of 1 to 32 billion parameters, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. Kezins argues that architectures built on the same unexplained-information bound inherit this attack surface, and recommends calibrating tolerances against local token entropy rather than benign traffic.",
        "response": null,
        "sources": [
          "S-1507",
          "S-0015"
        ],
        "helps": [
          {
            "by": "M-0002",
            "how": "Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata."
          }
        ]
      },
      {
        "mech": "M-0024",
        "n": 2,
        "title": "Information the declared computation explains is not bounded",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The bound limits unexplained bits only. Outputs that the declared computation fully explains can still carry valuable information: a compression study notes that an adversary with inference access can extract more proprietary information per bit than naive transmission allows.",
        "response": null,
        "sources": [
          "S-1508",
          "S-0019"
        ]
      },
      {
        "mech": "M-0024",
        "n": 3,
        "title": "Channels other than checked outputs are outside the bound",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The inference-verification scheme treats side channels as out of scope. A low-trust system design argues that suppressing physical covert bandwidth below kilobits per second is much more achievable than aiming for zero, and that a malicious device can leak one bit of information by deliberately outputting a wrong result.",
        "response": null,
        "sources": [
          "S-0015",
          "S-0018"
        ],
        "helps": [
          {
            "by": "M-0022",
            "how": "Physical side channels need separate suppression, which is this mechanism's purpose."
          }
        ]
      },
      {
        "mech": "M-0024",
        "n": 4,
        "title": "The facility-level design is untested",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The compute-verification architecture is described with protocol details, potential attacks and prototyping plans, but no prototype results have been published.",
        "response": null,
        "sources": [
          "S-0019"
        ]
      }
    ],
    "criticalMechanisms": [],
    "significantMechanisms": [
      "M-0024"
    ],
    "familyContext": [],
    "minor": 0,
    "minorFindings": [],
    "minorBy": [],
    "notDemonstrated": [],
    "newChip": []
  },
  "findings": [
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 1,
      "title": "Prompt-controlled entropy inflation widens the covert channel",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Gumbel-based inference verification tolerates token choices that honest GPU nondeterminism could produce, and the size of that tolerated set grows with the model's output entropy. Kezins, an independent researcher, showed that an adversary who controls the prompt distribution can raise output entropy and roughly double the bits leaked per token. Across six models of 1 to 32 billion parameters, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. Kezins argues that architectures built on the same unexplained-information bound inherit this attack surface, and recommends calibrating tolerances against local token entropy rather than benign traffic.",
      "response": null,
      "sources": [
        "S-1507",
        "S-0015"
      ],
      "helps": [
        {
          "by": "M-0002",
          "how": "Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata."
        }
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 2,
      "title": "Information the declared computation explains is not bounded",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The bound limits unexplained bits only. Outputs that the declared computation fully explains can still carry valuable information: a compression study notes that an adversary with inference access can extract more proprietary information per bit than naive transmission allows.",
      "response": null,
      "sources": [
        "S-1508",
        "S-0019"
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 3,
      "title": "Channels other than checked outputs are outside the bound",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The inference-verification scheme treats side channels as out of scope. A low-trust system design argues that suppressing physical covert bandwidth below kilobits per second is much more achievable than aiming for zero, and that a malicious device can leak one bit of information by deliberately outputting a wrong result.",
      "response": null,
      "sources": [
        "S-0015",
        "S-0018"
      ],
      "helps": [
        {
          "by": "M-0022",
          "how": "Physical side channels need separate suppression, which is this mechanism's purpose."
        }
      ]
    },
    {
      "mech": "M-0024",
      "record": "M-0024",
      "n": 4,
      "title": "The facility-level design is untested",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The compute-verification architecture is described with protocol details, potential attacks and prototyping plans, but no prototype results have been published.",
      "response": null,
      "sources": [
        "S-0019"
      ]
    }
  ],
  "possible_additions": [
    {
      "id": "M-0002",
      "title": "Deterministic and bit-exact inference",
      "url": "https://trustbutveri.fyi/mechanisms/deterministic-inference/",
      "readiness": "R3",
      "fits_filters": false,
      "filter_issues": [
        {
          "filter": "tested",
          "level": "exclude",
          "short": "attack testing: analysis",
          "text": "Attack testing is analysis; the filter asks for at least red-teamed."
        }
      ],
      "reasons": [
        {
          "kind": "flaw",
          "mech": "M-0024",
          "n": 1,
          "title": "Prompt-controlled entropy inflation widens the covert channel",
          "severity": "significant",
          "how": "Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata."
        },
        {
          "kind": "blocker",
          "mech": "M-0024",
          "text": "Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata."
        }
      ]
    },
    {
      "id": "M-0022",
      "title": "Side-channel suppression for isolated facilities",
      "url": "https://trustbutveri.fyi/mechanisms/side-channel-suppression/",
      "readiness": "R1",
      "fits_filters": false,
      "filter_issues": [
        {
          "filter": "tested",
          "level": "exclude",
          "short": "attack testing: analysis",
          "text": "Attack testing is analysis; the filter asks for at least red-teamed."
        }
      ],
      "reasons": [
        {
          "kind": "flaw",
          "mech": "M-0024",
          "n": 3,
          "title": "Channels other than checked outputs are outside the bound",
          "severity": "significant",
          "how": "Physical side channels need separate suppression, which is this mechanism's purpose."
        },
        {
          "kind": "blocker",
          "mech": "M-0024",
          "text": "Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target."
        }
      ]
    },
    {
      "id": "M-0014",
      "title": "Bandwidth limits and compartmentalization",
      "url": "https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/",
      "readiness": "R2",
      "fits_filters": false,
      "filter_issues": [
        {
          "filter": "tested",
          "level": "exclude",
          "short": "attack testing: analysis",
          "text": "Attack testing is analysis; the filter asks for at least red-teamed."
        }
      ],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0024",
          "text": "The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound."
        }
      ]
    },
    {
      "id": "M-0001",
      "title": "Sampled inference recomputation",
      "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/",
      "readiness": "R3",
      "fits_filters": false,
      "filter_issues": [
        {
          "filter": "tested",
          "level": "exclude",
          "short": "attack testing: analysis",
          "text": "Attack testing is analysis; the filter asks for at least red-teamed."
        }
      ],
      "reasons": [
        {
          "kind": "prerequisite",
          "mech": "M-0024"
        }
      ]
    },
    {
      "id": "M-0013",
      "title": "Network taps and certifiers",
      "url": "https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/",
      "readiness": "R1",
      "fits_filters": false,
      "filter_issues": [
        {
          "filter": "tested",
          "level": "exclude",
          "short": "attack testing: analysis",
          "text": "Attack testing is analysis; the filter asks for at least red-teamed."
        }
      ],
      "reasons": [
        {
          "kind": "prerequisite",
          "mech": "M-0024"
        }
      ]
    }
  ],
  "goal": null,
  "design": null,
  "dependencies": {
    "prerequisites": [
      {
        "id": "M-0001",
        "neededBy": [
          "M-0024"
        ]
      },
      {
        "id": "M-0014",
        "neededBy": [
          "M-0024"
        ]
      },
      {
        "id": "M-0022",
        "neededBy": [
          "M-0024"
        ]
      },
      {
        "id": "M-0013",
        "neededBy": [
          "M-0024"
        ]
      }
    ],
    "shared": [],
    "blockers": [
      {
        "mech": "M-0024",
        "n": 1,
        "text": "The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0014",
        "sources": [
          "S-0019"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0024",
        "n": 2,
        "text": "Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0022",
        "sources": [
          "S-0018",
          "S-0015"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0024",
        "n": 3,
        "text": "Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata.",
        "theme": "protocol-soundness",
        "blocked_by": "M-0002",
        "sources": [
          "S-1507",
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0024",
        "n": 4,
        "text": "Recomputation over confidential weights and inputs needs a protected setting: prover recomputation in a verifier-controlled enclosure, verifier recomputation in a prover-controlled enclosure, or zero-knowledge proofs.",
        "theme": "privacy-leakage",
        "blocked_by": null,
        "sources": [
          "S-0019"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0024",
        "n": 5,
        "text": "No prototype of the facility-level architecture exists to red-team.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-0019"
        ],
        "inProposal": null
      }
    ]
  },
  "exposure": {
    "weights": {
      "shown": [],
      "partial": [
        "M-0024"
      ],
      "hidden": [],
      "none": [],
      "unknown": []
    },
    "io": {
      "shown": [],
      "partial": [
        "M-0024"
      ],
      "hidden": [],
      "none": [],
      "unknown": []
    },
    "training": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0024"
      ],
      "unknown": []
    }
  },
  "implementations": [
    {
      "mechanism": "M-0024",
      "selected": null,
      "implementations": []
    }
  ],
  "sources": [
    {
      "id": "S-0019",
      "title": "Verifying AI Compute by Bounding Unexplained Information Exfiltration",
      "authors": "J. Petrie & Y. Mühlhäuser",
      "year": 2026,
      "url": "https://openreview.net/forum?id=qtgG5HZSsk",
      "path": "/sources/petrie-bounding-unexplained-information-exfiltration/"
    },
    {
      "id": "S-0015",
      "title": "Verifying LLM Inference to Detect Model Weight Exfiltration",
      "authors": "R. Rinberg et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2511.02620",
      "path": "/sources/rinberg-verifying-llm-inference-weight-exfiltration/"
    },
    {
      "id": "S-1507",
      "title": "Adversarial Entropy Inflation Against Gumbel-Based Inference Verification",
      "authors": "N. Kezins",
      "year": 2026,
      "url": "https://arxiv.org/abs/2608.23375",
      "path": "/sources/kezins-adversarial-entropy-inflation/"
    },
    {
      "id": "S-1508",
      "title": "Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains",
      "authors": "R. Rinberg et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2604.02343",
      "path": "/sources/rinberg-haiku-to-opus-compression/"
    },
    {
      "id": "S-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/"
    }
  ]
}