{
  "schema_version": "1.3",
  "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0004,M-0009,M-0019&ready=R2",
  "data_generated": "2026-10-09",
  "definitions": {
    "methodology": "https://trustbutveri.fyi/about/methodology/",
    "readiness": "https://trustbutveri.fyi/about/readiness/",
    "filters": [
      {
        "id": "prover",
        "label": "Prover",
        "question": "How far can the party being checked be trusted?",
        "options": [
          {
            "value": "cooperative",
            "label": "Cooperative"
          },
          {
            "value": "semi-trusted",
            "label": "Semi-trusted"
          },
          {
            "value": "adversarial",
            "label": "Adversarial"
          }
        ],
        "rule": "Keeps mechanisms whose threat model holds against at least this prover. Adversarial is the strongest assumption.",
        "about": "The prover is the party being checked. Semi-trusted designs rely on part of its stack: usually the chip vendor's hardware root of trust, its firmware or counters, or its supply-chain records. Adversarial designs aim to hold even if it cheats wherever the checks allow, within their stated assumptions."
      },
      {
        "id": "onsite",
        "label": "Verifier devices on site",
        "question": "May the verifier install its own hardware at the prover's sites?",
        "options": [
          {
            "value": "no",
            "label": "Not allowed"
          }
        ],
        "rule": "\"Not allowed\" removes mechanisms that need a retrofit device, such as a network tap or a sealed sensor.",
        "about": "Some mechanisms need a device the verifier owns or trusts at the prover's facility, such as a network tap, a bandwidth limiter or a sealed sensor. Choose Not allowed when the setting rules that out. Inspectors are not covered."
      },
      {
        "id": "coop",
        "label": "Prover cooperation",
        "question": "How much must the prover take part?",
        "options": [
          {
            "value": "partial",
            "label": "Partial at most"
          },
          {
            "value": "none",
            "label": "Not required"
          }
        ],
        "rule": "\"Partial at most\" removes mechanisms that need the prover's active participation. \"Not required\" keeps only those that work without it.",
        "about": "Required: the prover takes part, for example by logging requests, producing proofs or opening records. Partial: some access, such as installing a device. Not required: works from outside, such as satellite imagery."
      },
      {
        "id": "chips",
        "label": "Chips",
        "question": "May the proposal depend on new chip designs?",
        "options": [
          {
            "value": "existing",
            "label": "Existing chips only"
          }
        ],
        "rule": "\"Existing chips only\" removes mechanisms that need changes to future chip designs.",
        "about": "New chip features take years to reach a deployed fleet and cover only chips made after they ship. Mechanisms that use shipping features, such as trusted execution environments or performance counters, stay."
      },
      {
        "id": "ready",
        "label": "Minimum development status",
        "question": "Development status",
        "options": [
          {
            "value": "R1",
            "label": "Proposed"
          },
          {
            "value": "R2",
            "label": "Research demonstration"
          },
          {
            "value": "R3",
            "label": "Operational use"
          },
          {
            "value": "R4",
            "label": "Legacy independent-evaluation filter",
            "legacy": true
          }
        ],
        "rule": "Keeps mechanisms whose readiness level is at least this one.",
        "about": "A level describes the public evidence for a mechanism's stated use, not its cost or feasibility. R3 can still have open critical flaws."
      },
      {
        "id": "tested",
        "label": "Attack testing",
        "question": "How hard has each mechanism been attacked in public?",
        "options": [
          {
            "value": "analysis",
            "label": "Published analysis"
          },
          {
            "value": "red-teamed",
            "label": "Red-teamed"
          },
          {
            "value": "independent-red-team",
            "label": "Independent red-team"
          }
        ],
        "rule": "Keeps mechanisms whose strongest published attack testing is at least this.",
        "about": "The strongest published attempt to break the mechanism for its verification use: a security analysis, red-teaming by its developers or collaborators, or a red team independent of them."
      },
      {
        "id": "hide",
        "label": "Keep hidden from the verifier",
        "question": "What must the verifier never see?",
        "options": [
          {
            "value": "weights",
            "label": "Model weights"
          },
          {
            "value": "io",
            "label": "Inputs and outputs"
          },
          {
            "value": "training",
            "label": "Training data"
          }
        ],
        "rule": "Removes mechanisms that show the asset to the verifier. Conditional or unspecified exposure stays with a note and needs checking against the privacy requirement.",
        "about": "Model weights: the checked model's parameters. Inputs and outputs: the requests a deployed model serves and its responses. Training data: what a model was trained on. Each mechanism's exposure is the editors' reading of its record: shown, depends on the design (kept, with a note), hidden, not involved, or unspecified for a selected implementation. Code and configuration are not covered yet."
      }
    ],
    "exposure": "For model weights, inputs and outputs, and training data. This is the editors' reading of each mechanism's record (its threat model, how it works and its limitations), not a field of the record. Shown: the verifier sees it. Depends: on the design or variant, or the verifier sees only samples. Hidden: the verifier sees only commitments, hashes, proofs or results. Not involved: the record does not handle it. Unspecified: the selected implementation has no asset-specific assessment here.",
    "claim_status": {
      "addressed": "A mechanism in the proposal is aimed at this claim and is not excluded by the filters.",
      "partly-addressed": "Only supporting mechanisms, or mechanisms aimed at it that the filters exclude.",
      "unaddressed": "No mechanism in the proposal addresses this claim."
    },
    "finding_classification": {
      "failure": {
        "label": "Known failures",
        "singular": "Known failure",
        "anchor": "known-flaws"
      },
      "scope-limitation": {
        "label": "Scope limitations",
        "singular": "Scope limitation",
        "anchor": "scope-limitations"
      },
      "open-question": {
        "label": "Open questions",
        "singular": "Open question",
        "anchor": "open-questions"
      }
    },
    "finding_scope": "Evidence scope describes where a finding was demonstrated; it does not establish applicability to every implementation in the mechanism family.",
    "claim_finding_scope": "open_critical_findings names active failures on the assessed records; open_critical_context names conditional family failures whose implementation applicability is unassessed.",
    "legacy_status": "The status field retains covered/partial/none for compatibility. It names claim links, never successful verification. Use claim_status and status_label for presentation."
  },
  "filters": {
    "prover": "",
    "onsite": "",
    "coop": "",
    "chips": "",
    "ready": "R2",
    "tested": "",
    "hide": []
  },
  "mechanisms_passing_filters": 15,
  "claims": [],
  "mechanisms": [
    {
      "id": "M-0004",
      "title": "Zero-knowledge proofs of inference",
      "url": "https://trustbutveri.fyi/mechanisms/zk-proofs-of-inference/",
      "assessment_record": {
        "id": "M-0004",
        "title": "Zero-knowledge proofs of inference",
        "url": "https://trustbutveri.fyi/mechanisms/zk-proofs-of-inference/"
      },
      "finding_counts": {
        "failure": 0,
        "scope_limitation": 4,
        "open_question": 0,
        "open_failures": {
          "critical": 0,
          "significant": 0,
          "minor": 0
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R2",
        "scope": "proving a language model's output follows from committed weights, against a cheating prover",
        "confidence": "medium",
        "evidence": [
          "S-0023",
          "S-1108",
          "S-0021",
          "S-0068",
          "S-1101",
          "S-0024",
          "S-0070",
          "S-1807",
          "S-1808",
          "S-1112"
        ]
      },
      "development_status": {
        "code": "R2",
        "label": "Research demonstration",
        "short": "Research demo",
        "rank": 2,
        "legacy_code": "R2"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "independent-red-team",
          "label": "Published attack testing",
          "kind": "practical",
          "attribution": "Independent team"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [],
        "open_failures": {
          "critical": 0,
          "significant": 0,
          "minor": 0
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "none",
        "prover_cooperation": "required",
        "adversarial_evaluation": "independent-red-team"
      },
      "claims": [],
      "exposure": {
        "weights": "hidden",
        "io": "shown",
        "training": "none",
        "note": "The weights stay committed and hidden; the verifier knows each input and output it checks."
      },
      "family_finding_context": [],
      "filter_issues": []
    },
    {
      "id": "M-0009",
      "title": "Hardware-enabled guarantees (flexHEG) and guarantee processors",
      "url": "https://trustbutveri.fyi/mechanisms/flexheg-guarantee-processors/",
      "assessment_record": {
        "id": "M-0009",
        "title": "Hardware-enabled guarantees (flexHEG) and guarantee processors",
        "url": "https://trustbutveri.fyi/mechanisms/flexheg-guarantee-processors/"
      },
      "finding_counts": {
        "failure": 3,
        "scope_limitation": 2,
        "open_question": 1,
        "open_failures": {
          "critical": 0,
          "significant": 3,
          "minor": 0
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R1",
        "scope": "checking and enforcing training-compute limits on chips, against adversaries up to states",
        "confidence": "medium",
        "evidence": [
          "S-0035",
          "S-1204",
          "S-1205",
          "S-0057",
          "S-0056",
          "S-0006"
        ]
      },
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1204",
              "S-0057"
            ]
          },
          {
            "n": 2,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1204"
            ]
          },
          {
            "n": 4,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1204"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 3,
          "minor": 0
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "new-chip",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "hidden",
        "io": "hidden",
        "training": "hidden",
        "note": "The guarantee processor sees the chip's traffic inside a sealed enclosure and reports only whether rules were kept."
      },
      "family_finding_context": [],
      "filter_issues": [
        {
          "filter": "ready",
          "level": "exclude",
          "short": "development: Proposed",
          "text": "Development status: Proposed. Minimum: Research demonstration."
        }
      ]
    },
    {
      "id": "M-0019",
      "title": "Chip registries and manufacturing records",
      "url": "https://trustbutveri.fyi/mechanisms/chip-registries-and-manufacturing-records/",
      "assessment_record": {
        "id": "M-0019",
        "title": "Chip registries and manufacturing records",
        "url": "https://trustbutveri.fyi/mechanisms/chip-registries-and-manufacturing-records/"
      },
      "finding_counts": {
        "failure": 1,
        "scope_limitation": 2,
        "open_question": 0,
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R1",
        "scope": "a checkable record of which chips were made and who declared owning them",
        "confidence": "medium",
        "evidence": [
          "S-0002",
          "S-1402",
          "S-1408",
          "S-0007"
        ]
      },
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 2,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1402"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "assessed_properties": {
        "threat_model": "semi-trusted",
        "hardware_requirement": "existing-features",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "none",
        "io": "none",
        "training": "none",
        "note": "Records chip identities and owners; it does not handle model data."
      },
      "family_finding_context": [],
      "filter_issues": [
        {
          "filter": "ready",
          "level": "exclude",
          "short": "development: Proposed",
          "text": "Development status: Proposed. Minimum: Research demonstration."
        }
      ]
    }
  ],
  "strengths": {
    "covered": [],
    "production": [],
    "operationalUse": [],
    "adversarial": [
      "M-0004"
    ],
    "noNewHardware": [
      "M-0004"
    ],
    "mitigated": [],
    "notCounted": [
      "M-0009",
      "M-0019"
    ]
  },
  "properties": {
    "covered": [],
    "production": [],
    "operationalUse": [],
    "adversarial": [
      "M-0004"
    ],
    "noNewHardware": [
      "M-0004"
    ],
    "mitigated": [],
    "notCounted": [
      "M-0009",
      "M-0019"
    ]
  },
  "attack_testing": [
    {
      "id": "M-0004",
      "record": "M-0004",
      "evaluation": "independent-red-team",
      "in_setting": true
    },
    {
      "id": "M-0009",
      "record": "M-0009",
      "evaluation": "analysis",
      "in_setting": false
    },
    {
      "id": "M-0019",
      "record": "M-0019",
      "evaluation": "analysis",
      "in_setting": false
    }
  ],
  "selected_implementations": {},
  "weaknesses": {
    "gaps": [],
    "excluded": [
      {
        "id": "M-0009",
        "issues": [
          {
            "filter": "ready",
            "level": "exclude",
            "short": "development: Proposed",
            "text": "Development status: Proposed. Minimum: Research demonstration."
          }
        ]
      },
      {
        "id": "M-0019",
        "issues": [
          {
            "filter": "ready",
            "level": "exclude",
            "short": "development: Proposed",
            "text": "Development status: Proposed. Minimum: Research demonstration."
          }
        ]
      }
    ],
    "unlinked": [],
    "critical": [],
    "significant": [
      {
        "mech": "M-0009",
        "n": 1,
        "historical": false,
        "title": "State attackers can likely defeat current secure enclosures",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "The flexHEG authors write that \"nation-state attackers can likely compromise the best current secure enclosures\", and that the marginal cost of circumvention per device is hard to estimate. RAND similarly judges that anti-tamper measures \"would not be insurmountable for a determined and well-resourced adversary\", although they raise costs and can reveal tampering.",
        "response": null,
        "sources": [
          "S-1204",
          "S-0057"
        ]
      },
      {
        "mech": "M-0009",
        "n": 2,
        "historical": false,
        "title": "Firmware-only retrofits rely on Secure Boot, which fault injection can bypass",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Part II notes that the most common attack on Secure Boot replaces the firmware and applies a voltage glitch while the signature is being checked. It also notes that sophisticated actors may use microprobing or laser voltage probing to read key registers.",
        "response": null,
        "sources": [
          "S-1204"
        ]
      },
      {
        "mech": "M-0009",
        "n": 4,
        "historical": false,
        "title": "FLOP accounting can be laundered through external data",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Results of earlier or parallel workloads could be hidden in the \"external data\" fed to a device, which would falsify the total FLOP count unless the inputs are explained or time delays are imposed.",
        "response": null,
        "sources": [
          "S-1204"
        ]
      },
      {
        "mech": "M-0019",
        "n": 2,
        "historical": false,
        "title": "Documents and serial numbers can be forged",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Avellar and Grunewald note that export documents can be forged, that companies can hide information behind obscure corporate structures, and that it may be possible to forge serial numbers on chips and racks. They recommend cryptographic attestation of a powered-on chip as an extra check.",
        "response": null,
        "sources": [
          "S-1402"
        ]
      }
    ],
    "criticalMechanisms": [],
    "significantMechanisms": [
      "M-0009",
      "M-0019"
    ],
    "familyContext": [],
    "scopeLimitations": [
      {
        "mech": "M-0004",
        "n": 1,
        "historical": false,
        "title": "The proof covers a fixed-point approximation, not the floating-point model",
        "classification": "scope-limitation",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Current ZK inference systems prove a quantised version of the network. zkLLM scales values by 2^16 and reports small perplexity changes. Attestable reports quantising matrix multiplications to 8-bit integers while proving other operations in floating point. A verifier therefore learns about the proof-friendly variant, and must separately accept that this variant is the declared model. Trail of Bits built a ResNet-18 backdoor that is dormant in the full-precision model and active after ezkl's quantisation; whether it persists through proving was left for further investigation. A verification system design notes that ZKPs can emulate floating-point operations. Rounding makes floating-point results depend on summation order, so bit-for-bit replay of an accelerator's results needs its original reduction tree. The report calls emulating that tree inside a ZKP an open, intricate problem and asks what it would cost.",
        "response": null,
        "sources": [
          "S-0023",
          "S-1101",
          "S-0070",
          "S-0018"
        ]
      },
      {
        "mech": "M-0004",
        "n": 2,
        "historical": false,
        "title": "A proof speaks only for the computations that were proven",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Attestable writes that \"a proof of some computation is not a proof of all computation\", and that a proof cannot discover a datacenter that was never declared. Proofs of inference do not by themselves show that no other workload ran on the same or other hardware.",
        "response": null,
        "sources": [
          "S-1102"
        ],
        "helps": [
          {
            "by": "M-0007",
            "how": "The record names proof-of-work accounting as the kind of compute accounting needed to show that proven inference was the only work done."
          }
        ]
      },
      {
        "mech": "M-0004",
        "n": 3,
        "historical": false,
        "title": "The model architecture is disclosed",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "minor",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "ZKML \"requires that the model architecture (but not weights) is revealed\", and zkLLM assumes a publicly known model structure. Architecture can be commercially sensitive.",
        "response": null,
        "sources": [
          "S-0021",
          "S-0023"
        ]
      },
      {
        "mech": "M-0004",
        "n": 4,
        "historical": false,
        "title": "Proofs do not bind computational effort (Hollow-LLM)",
        "classification": "scope-limitation",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Researchers at the University of Southern California show that a proof of inference certifies that an output is consistent with committed weights under the declared architecture, but not how much computation produced it. In their Hollow-LLM attack, a provider keeps the declared architecture and parameter count but commits to \"ghost weights\". Some layers pass their inputs through unchanged, and wide layers carry the signal in a small subspace, so a much smaller inner model does the real work. The ghost weights satisfy the verification circuit and yield valid proofs.\nThe authors ran the attack with the proof procedure of zkGPT, a separate ZK inference system, on a 6-layer, 512-dimensional transformer declared as up to 12 layers and 1,024 dimensions. Outputs were identical to the inner model's, and serving cost stayed at the inner model's level. An honest model of the declared size cost 2.4 times as much to prefill and 3.1 times as much to decode. Proving cost still grew with the declared architecture.\nThe authors note that results may be served before any proof, with the provider building the witness only when a call is selected for audit. They describe their constructions as \"compatible with state-of-the-art zkLLM pipelines\", and state that the attack does not imply a flaw in the proof system itself. They propose challenge-based audits and ablation tests, which raise the cost of cheating but give no guarantee.",
        "response": null,
        "sources": [
          "S-1112"
        ]
      },
      {
        "mech": "M-0009",
        "n": 3,
        "historical": false,
        "title": "Many important rules cannot be checked on-chip",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Malicious intent \"is not a technical property observable on-chip\", and misuse depends on what is done with a computation's results. A guarantee processor cannot easily tell whether a network is the whole system or one expert in a mixture-of-experts system. Part III judges that a fully local ruleset \"may not be entirely feasible\" for the same reason.",
        "response": null,
        "sources": [
          "S-0035",
          "S-1205"
        ]
      },
      {
        "mech": "M-0009",
        "n": 6,
        "historical": false,
        "title": "Coverage stops at flexHEG-equipped chips",
        "classification": "scope-limitation",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Motivated actors will always be able to use some compute that is not flexHEG-equipped. Recalling existing consumer GPUs would likely be impractical, and reaching perfect coverage, or conclusively proving that no secret government data centres exist, would be \"practically quite difficult\".",
        "response": null,
        "sources": [
          "S-0035",
          "S-1205"
        ],
        "helps": [
          {
            "by": "M-0019",
            "how": "Accounts for which chips exist and who holds them."
          },
          {
            "by": "M-0020",
            "how": "Looks for undeclared facilities that hold other chips."
          }
        ]
      },
      {
        "mech": "M-0019",
        "n": 1,
        "historical": false,
        "title": "Records cover only chips that were recorded",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "A registry or commitment accounts only for chips entered into it. Cankaya asks how a verifier would know it had found all chips, or how much \"dark compute\" remains, and notes that a fraudulent original record would mean unregistered chips had been made in advance. Halstead and Larsen propose reconstructing earlier production by auditing upstream suppliers.",
        "response": null,
        "sources": [
          "S-1408",
          "S-1410"
        ],
        "helps": [
          {
            "by": "M-0020",
            "how": "Looks for large data centres that were never declared, which a registry cannot show."
          }
        ]
      },
      {
        "mech": "M-0019",
        "n": 3,
        "historical": false,
        "title": "Insiders could alter records before they are fixed",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Cankaya argues that insiders who can photograph process secrets could also tamper with production records. A commitment makes changes after publication detectable, but it cannot show that the records were accurate when committed.",
        "response": null,
        "sources": [
          "S-1408"
        ]
      }
    ],
    "openQuestions": [
      {
        "mech": "M-0009",
        "n": 5,
        "historical": false,
        "title": "Supply-chain diversion and hidden backdoors",
        "classification": "open-question",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Components could be diverted before a guarantee processor is added, and backdoors could be introduced during design or manufacturing. Open-source designs and physical scans of randomly selected chips are proposed as countermeasures. Part III proposes international oversight of production and extensive testing of a random sample of finished devices.",
        "response": null,
        "sources": [
          "S-1204",
          "S-1205"
        ],
        "helps": [
          {
            "by": "M-0019",
            "how": "Records each chip's identity and owner from the fab onwards, which bears on diversion before a guarantee processor is fitted. It does not address hidden backdoors."
          }
        ]
      }
    ],
    "minor": 0,
    "minorFindings": [],
    "minorBy": [],
    "notDemonstrated": [
      "M-0009",
      "M-0019"
    ],
    "newChip": [
      "M-0009"
    ]
  },
  "findings": [
    {
      "mech": "M-0004",
      "record": "M-0004",
      "n": 1,
      "historical": false,
      "title": "The proof covers a fixed-point approximation, not the floating-point model",
      "classification": "scope-limitation",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Current ZK inference systems prove a quantised version of the network. zkLLM scales values by 2^16 and reports small perplexity changes. Attestable reports quantising matrix multiplications to 8-bit integers while proving other operations in floating point. A verifier therefore learns about the proof-friendly variant, and must separately accept that this variant is the declared model. Trail of Bits built a ResNet-18 backdoor that is dormant in the full-precision model and active after ezkl's quantisation; whether it persists through proving was left for further investigation. A verification system design notes that ZKPs can emulate floating-point operations. Rounding makes floating-point results depend on summation order, so bit-for-bit replay of an accelerator's results needs its original reduction tree. The report calls emulating that tree inside a ZKP an open, intricate problem and asks what it would cost.",
      "response": null,
      "sources": [
        "S-0023",
        "S-1101",
        "S-0070",
        "S-0018"
      ]
    },
    {
      "mech": "M-0004",
      "record": "M-0004",
      "n": 2,
      "historical": false,
      "title": "A proof speaks only for the computations that were proven",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Attestable writes that \"a proof of some computation is not a proof of all computation\", and that a proof cannot discover a datacenter that was never declared. Proofs of inference do not by themselves show that no other workload ran on the same or other hardware.",
      "response": null,
      "sources": [
        "S-1102"
      ],
      "helps": [
        {
          "by": "M-0007",
          "how": "The record names proof-of-work accounting as the kind of compute accounting needed to show that proven inference was the only work done."
        }
      ]
    },
    {
      "mech": "M-0004",
      "record": "M-0004",
      "n": 3,
      "historical": false,
      "title": "The model architecture is disclosed",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "minor",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "ZKML \"requires that the model architecture (but not weights) is revealed\", and zkLLM assumes a publicly known model structure. Architecture can be commercially sensitive.",
      "response": null,
      "sources": [
        "S-0021",
        "S-0023"
      ]
    },
    {
      "mech": "M-0004",
      "record": "M-0004",
      "n": 4,
      "historical": false,
      "title": "Proofs do not bind computational effort (Hollow-LLM)",
      "classification": "scope-limitation",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Researchers at the University of Southern California show that a proof of inference certifies that an output is consistent with committed weights under the declared architecture, but not how much computation produced it. In their Hollow-LLM attack, a provider keeps the declared architecture and parameter count but commits to \"ghost weights\". Some layers pass their inputs through unchanged, and wide layers carry the signal in a small subspace, so a much smaller inner model does the real work. The ghost weights satisfy the verification circuit and yield valid proofs.\nThe authors ran the attack with the proof procedure of zkGPT, a separate ZK inference system, on a 6-layer, 512-dimensional transformer declared as up to 12 layers and 1,024 dimensions. Outputs were identical to the inner model's, and serving cost stayed at the inner model's level. An honest model of the declared size cost 2.4 times as much to prefill and 3.1 times as much to decode. Proving cost still grew with the declared architecture.\nThe authors note that results may be served before any proof, with the provider building the witness only when a call is selected for audit. They describe their constructions as \"compatible with state-of-the-art zkLLM pipelines\", and state that the attack does not imply a flaw in the proof system itself. They propose challenge-based audits and ablation tests, which raise the cost of cheating but give no guarantee.",
      "response": null,
      "sources": [
        "S-1112"
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 1,
      "historical": false,
      "title": "State attackers can likely defeat current secure enclosures",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "The flexHEG authors write that \"nation-state attackers can likely compromise the best current secure enclosures\", and that the marginal cost of circumvention per device is hard to estimate. RAND similarly judges that anti-tamper measures \"would not be insurmountable for a determined and well-resourced adversary\", although they raise costs and can reveal tampering.",
      "response": null,
      "sources": [
        "S-1204",
        "S-0057"
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 2,
      "historical": false,
      "title": "Firmware-only retrofits rely on Secure Boot, which fault injection can bypass",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Part II notes that the most common attack on Secure Boot replaces the firmware and applies a voltage glitch while the signature is being checked. It also notes that sophisticated actors may use microprobing or laser voltage probing to read key registers.",
      "response": null,
      "sources": [
        "S-1204"
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 3,
      "historical": false,
      "title": "Many important rules cannot be checked on-chip",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Malicious intent \"is not a technical property observable on-chip\", and misuse depends on what is done with a computation's results. A guarantee processor cannot easily tell whether a network is the whole system or one expert in a mixture-of-experts system. Part III judges that a fully local ruleset \"may not be entirely feasible\" for the same reason.",
      "response": null,
      "sources": [
        "S-0035",
        "S-1205"
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 4,
      "historical": false,
      "title": "FLOP accounting can be laundered through external data",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Results of earlier or parallel workloads could be hidden in the \"external data\" fed to a device, which would falsify the total FLOP count unless the inputs are explained or time delays are imposed.",
      "response": null,
      "sources": [
        "S-1204"
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 5,
      "historical": false,
      "title": "Supply-chain diversion and hidden backdoors",
      "classification": "open-question",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Components could be diverted before a guarantee processor is added, and backdoors could be introduced during design or manufacturing. Open-source designs and physical scans of randomly selected chips are proposed as countermeasures. Part III proposes international oversight of production and extensive testing of a random sample of finished devices.",
      "response": null,
      "sources": [
        "S-1204",
        "S-1205"
      ],
      "helps": [
        {
          "by": "M-0019",
          "how": "Records each chip's identity and owner from the fab onwards, which bears on diversion before a guarantee processor is fitted. It does not address hidden backdoors."
        }
      ]
    },
    {
      "mech": "M-0009",
      "record": "M-0009",
      "n": 6,
      "historical": false,
      "title": "Coverage stops at flexHEG-equipped chips",
      "classification": "scope-limitation",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Motivated actors will always be able to use some compute that is not flexHEG-equipped. Recalling existing consumer GPUs would likely be impractical, and reaching perfect coverage, or conclusively proving that no secret government data centres exist, would be \"practically quite difficult\".",
      "response": null,
      "sources": [
        "S-0035",
        "S-1205"
      ],
      "helps": [
        {
          "by": "M-0019",
          "how": "Accounts for which chips exist and who holds them."
        },
        {
          "by": "M-0020",
          "how": "Looks for undeclared facilities that hold other chips."
        }
      ]
    },
    {
      "mech": "M-0019",
      "record": "M-0019",
      "n": 1,
      "historical": false,
      "title": "Records cover only chips that were recorded",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "A registry or commitment accounts only for chips entered into it. Cankaya asks how a verifier would know it had found all chips, or how much \"dark compute\" remains, and notes that a fraudulent original record would mean unregistered chips had been made in advance. Halstead and Larsen propose reconstructing earlier production by auditing upstream suppliers.",
      "response": null,
      "sources": [
        "S-1408",
        "S-1410"
      ],
      "helps": [
        {
          "by": "M-0020",
          "how": "Looks for large data centres that were never declared, which a registry cannot show."
        }
      ]
    },
    {
      "mech": "M-0019",
      "record": "M-0019",
      "n": 2,
      "historical": false,
      "title": "Documents and serial numbers can be forged",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Avellar and Grunewald note that export documents can be forged, that companies can hide information behind obscure corporate structures, and that it may be possible to forge serial numbers on chips and racks. They recommend cryptographic attestation of a powered-on chip as an extra check.",
      "response": null,
      "sources": [
        "S-1402"
      ]
    },
    {
      "mech": "M-0019",
      "record": "M-0019",
      "n": 3,
      "historical": false,
      "title": "Insiders could alter records before they are fixed",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Cankaya argues that insiders who can photograph process secrets could also tamper with production records. A commitment makes changes after publication detectable, but it cannot show that the records were accurate when committed.",
      "response": null,
      "sources": [
        "S-1408"
      ]
    }
  ],
  "possible_additions": [
    {
      "id": "M-0017",
      "title": "Tamper evidence for verifier devices",
      "url": "https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/",
      "readiness": "R2",
      "development_status": {
        "code": "R2",
        "label": "Research demonstration",
        "short": "Research demo",
        "rank": 2,
        "legacy_code": "R2"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1317",
              "S-1318"
            ]
          },
          {
            "n": 3,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1315",
              "S-0052",
              "S-3261"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0009",
          "text": "State-level attackers who hold the hardware can likely compromise the best current secure enclosures."
        }
      ]
    },
    {
      "id": "M-0008",
      "title": "TEE remote attestation for AI workloads",
      "url": "https://trustbutveri.fyi/mechanisms/tee-remote-attestation/",
      "readiness": "R3",
      "development_status": {
        "code": "R3",
        "label": "Operational use",
        "short": "Operational use",
        "rank": 3,
        "legacy_code": "R3"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "independent-red-team",
          "label": "Published attack testing",
          "kind": "practical",
          "attribution": "Independent team"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "critical",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1202",
              "S-3126",
              "S-0012",
              "S-1206",
              "S-0014",
              "S-1210",
              "S-1212",
              "S-3127"
            ]
          },
          {
            "n": 2,
            "severity": "critical",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1210",
              "S-1211"
            ]
          },
          {
            "n": 3,
            "severity": "critical",
            "status": "mitigated",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1212",
              "S-1213",
              "S-3127",
              "S-3128"
            ]
          },
          {
            "n": 4,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1202"
            ]
          },
          {
            "n": 5,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-0012",
              "S-0009",
              "S-0014",
              "S-3123",
              "S-3129"
            ]
          },
          {
            "n": 8,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-0014",
              "S-0009",
              "S-3130",
              "S-3131"
            ]
          }
        ],
        "open_failures": {
          "critical": 2,
          "significant": 3,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "prerequisite",
          "mech": "M-0009"
        }
      ]
    },
    {
      "id": "M-0007",
      "title": "Proofs of useful work for capacity accounting",
      "url": "https://trustbutveri.fyi/mechanisms/proofs-of-useful-work/",
      "readiness": "R1",
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 3,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1105"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "fits_filters": false,
      "filter_issues": [
        {
          "filter": "ready",
          "level": "exclude",
          "short": "development: Proposed",
          "text": "Development status: Proposed. Minimum: Research demonstration."
        }
      ],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0004",
          "text": "Showing that proven inference was the only work done needs a compute-accounting mechanism such as proof-of-work accounting, which is only proposed."
        }
      ]
    }
  ],
  "goal": null,
  "design": null,
  "dependencies": {
    "prerequisites": [
      {
        "id": "M-0008",
        "neededBy": [
          "M-0009"
        ]
      }
    ],
    "shared": [],
    "blockers": [
      {
        "mech": "M-0004",
        "n": 1,
        "historical": false,
        "text": "Proving takes about 13 minutes (803 seconds) per 2,048-token forward pass of a 13B model on one A100, and a verification system design calls the overhead heavy.",
        "theme": "performance-compatibility",
        "blocked_by": null,
        "sources": [
          "S-0023",
          "S-0018"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0004",
        "n": 2,
        "historical": false,
        "text": "ZKML and zkLLM prove fixed-point arithmetic, and a verification system design calls emulating an accelerator's original floating-point reduction tree inside a zero-knowledge proof, which bit-for-bit replay needs, an open and intricate problem whose cost is also unsettled.",
        "theme": "performance-compatibility",
        "blocked_by": null,
        "sources": [
          "S-0021",
          "S-0023",
          "S-0018"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0004",
        "n": 3,
        "historical": false,
        "text": "zkLLM's code is unaudited, interactive and archived; the one audited ZK inference library, ezkl, had high-severity circuit soundness bugs before its fixes.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-1108",
          "S-0070"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0004",
        "n": 4,
        "historical": false,
        "text": "Showing that proven inference was the only work done needs a compute-accounting mechanism such as proof-of-work accounting, which is only proposed.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0007",
        "sources": [
          "S-1102"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0009",
        "n": 1,
        "historical": false,
        "text": "Integrated flexHEG needs substantial help from the accelerator manufacturer, and the authors estimate 3.7–7.9 years, from when the manufacturer starts work, for such hardware to displace other accelerators in frontier development.",
        "theme": "access-governance",
        "blocked_by": null,
        "sources": [
          "S-1204"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0009",
        "n": 2,
        "historical": false,
        "text": "State-level attackers who hold the hardware can likely compromise the best current secure enclosures.",
        "theme": "hardware-trust",
        "blocked_by": "M-0017",
        "sources": [
          "S-1204",
          "S-0057"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0009",
        "n": 3,
        "historical": false,
        "text": "Rival states would need to trust the design and manufacture of guarantee processors and enclosures, for example through open design, redundant processors from each side or oversight of production.",
        "theme": "hardware-trust",
        "blocked_by": null,
        "sources": [
          "S-1205",
          "S-0035"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0009",
        "n": 4,
        "historical": false,
        "text": "Restricting future rule updates would need a formal language for rules, which the authors judge most likely infeasible for early flexHEG versions.",
        "theme": "protocol-soundness",
        "blocked_by": null,
        "sources": [
          "S-0035"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0009",
        "n": 5,
        "historical": false,
        "text": "Governing all relevant chips depends on knowing where they are, through chip registries and detection of undeclared facilities.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0019",
        "sources": [
          "S-1205"
        ],
        "inProposal": true
      },
      {
        "mech": "M-0019",
        "n": 1,
        "historical": false,
        "text": "No implementation of an AI chip registry has been publicly reported, and covering re-exports would need cooperation from re-exporters and foreign governments that may not be feasible everywhere.",
        "theme": "access-governance",
        "blocked_by": null,
        "sources": [
          "S-1402",
          "S-0002"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0019",
        "n": 2,
        "historical": false,
        "text": "Linking records to physical chips needs hard-to-spoof unique IDs and inspections.",
        "theme": "hardware-trust",
        "blocked_by": null,
        "sources": [
          "S-0002",
          "S-1402",
          "S-1408"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0019",
        "n": 3,
        "historical": false,
        "text": "Chips produced before a registry starts must be reconstructed from supplier records.",
        "theme": "coverage-hidden-compute",
        "blocked_by": null,
        "sources": [
          "S-1408",
          "S-1410"
        ],
        "inProposal": null
      }
    ]
  },
  "exposure": {
    "weights": {
      "shown": [],
      "partial": [],
      "hidden": [
        "M-0004",
        "M-0009"
      ],
      "none": [
        "M-0019"
      ],
      "unknown": []
    },
    "io": {
      "shown": [
        "M-0004"
      ],
      "partial": [],
      "hidden": [
        "M-0009"
      ],
      "none": [
        "M-0019"
      ],
      "unknown": []
    },
    "training": {
      "shown": [],
      "partial": [],
      "hidden": [
        "M-0009"
      ],
      "none": [
        "M-0004",
        "M-0019"
      ],
      "unknown": []
    }
  },
  "implementations": [
    {
      "mechanism": "M-0004",
      "selected": null,
      "implementations": [
        {
          "id": "I-0005",
          "title": "Attestable zero-knowledge inference prover",
          "url": "https://trustbutveri.fyi/implementations/attestable-zk-inference/"
        },
        {
          "id": "I-0014",
          "title": "EZKL",
          "url": "https://trustbutveri.fyi/implementations/ezkl/"
        },
        {
          "id": "I-0012",
          "title": "Low-trust AI compute verification system overview",
          "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
        },
        {
          "id": "I-0003",
          "title": "zkLLM",
          "url": "https://trustbutveri.fyi/implementations/zkllm/"
        }
      ]
    },
    {
      "mechanism": "M-0009",
      "selected": null,
      "implementations": []
    },
    {
      "mechanism": "M-0019",
      "selected": null,
      "implementations": []
    }
  ],
  "sources": [
    {
      "id": "S-0023",
      "title": "zkLLM: Zero Knowledge Proofs for Large Language Models",
      "authors": "H. Sun et al.",
      "year": 2024,
      "url": "https://doi.org/10.1145/3658644.3670334",
      "path": "/sources/sun-zkllm/"
    },
    {
      "id": "S-1108",
      "title": "zkllm-ccs2024: code for zkLLM: Zero Knowledge Proofs for Large Language Models",
      "authors": "H. Sun",
      "year": 2024,
      "url": "https://github.com/jvhs0706/zkllm-ccs2024",
      "path": "/sources/sun-zkllm-code/"
    },
    {
      "id": "S-0021",
      "title": "ZKML: An Optimizing System for ML Inference in Zero-Knowledge Proofs",
      "authors": "B.-J. Chen et al.",
      "year": 2024,
      "url": "https://doi.org/10.1145/3627703.3650088",
      "path": "/sources/chen-zkml/"
    },
    {
      "id": "S-0068",
      "title": "NanoZK: Privacy-Preserving Verifiable Inference for Large Language Models via Layerwise Zero-Knowledge Proofs",
      "authors": "Z. Wang",
      "year": 2026,
      "url": "https://arxiv.org/abs/2603.18046",
      "path": "/sources/wang-nanozk/"
    },
    {
      "id": "S-1101",
      "title": "Proving LLMs at Scale",
      "authors": "Attestable",
      "year": 2026,
      "url": "https://attestable.com/blog/proving-llms-scale",
      "path": "/sources/attestable-proving-llms-at-scale/"
    },
    {
      "id": "S-0024",
      "title": "Verifiable evaluations of machine learning models using zkSNARKs",
      "authors": "T. South et al.",
      "year": 2024,
      "url": "https://arxiv.org/abs/2402.02675",
      "path": "/sources/south-verifiable-evaluations-zksnarks/"
    },
    {
      "id": "S-0070",
      "title": "Zkonduit EZKL Security Assessment",
      "authors": "F. Casal et al.",
      "year": 2025,
      "url": "https://github.com/trailofbits/publications/blob/master/reviews/2025-03-zkonduit-ezkl-securityreview.pdf",
      "path": "/sources/trailofbits-ezkl-security-assessment/"
    },
    {
      "id": "S-1807",
      "title": "DeepProve-1: The First zkML System to Prove a Full LLM Inference",
      "authors": "Lagrange Labs",
      "year": 2025,
      "url": "https://lagrange.dev/blog/deepprove-1",
      "path": "/sources/lagrange-deepprove-1/"
    },
    {
      "id": "S-1808",
      "title": "Lagrange-Labs/deep-prove (GitHub repository)",
      "authors": "Lagrange Labs",
      "year": 2026,
      "url": "https://github.com/Lagrange-Labs/deep-prove",
      "path": "/sources/lagrange-deep-prove-code/"
    },
    {
      "id": "S-1112",
      "title": "Hollow-LLM Attack: Computationally Trivial Weights in Zero-Knowledge Verification of LLM Inference",
      "authors": "C. Gong et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2607.28884",
      "path": "/sources/gong-hollow-llm-attack/"
    },
    {
      "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-1102",
      "title": "Pacing AI Requires Proof",
      "authors": "Attestable",
      "year": 2026,
      "url": "https://attestable.com/blog/pacing-ai-requires-proof",
      "path": "/sources/attestable-pacing-ai-requires-proof/"
    },
    {
      "id": "S-0035",
      "title": "Flexible Hardware-Enabled Guarantees for AI Compute",
      "authors": "J. Petrie et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2506.15093",
      "path": "/sources/petrie-flexible-hardware-enabled-guarantees/"
    },
    {
      "id": "S-1204",
      "title": "Technical Options for Flexible Hardware-Enabled Guarantees",
      "authors": "J. Petrie & O. Aarne",
      "year": 2025,
      "url": "https://arxiv.org/abs/2506.03409",
      "path": "/sources/petrie-technical-options-flexheg/"
    },
    {
      "id": "S-1205",
      "title": "International Security Applications of Flexible Hardware-Enabled Guarantees",
      "authors": "O. Aarne & J. Petrie",
      "year": 2025,
      "url": "https://arxiv.org/abs/2506.15100",
      "path": "/sources/aarne-international-security-applications-flexheg/"
    },
    {
      "id": "S-0057",
      "title": "Hardware-Enabled Governance Mechanisms: Developing Technical Solutions to Exempt Items Otherwise Classified Under Export Control Classification Numbers 3A090 and 4A090",
      "authors": "G. Kulp et al.",
      "year": 2024,
      "url": "https://www.rand.org/pubs/working_papers/WRA3056-1.html",
      "path": "/sources/kulp-hardware-enabled-governance-mechanisms/"
    },
    {
      "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-0006",
      "title": "Hardware-Enabled Mechanisms for Verifying Responsible AI Development",
      "authors": "A. O'Gara et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2505.03742",
      "path": "/sources/ogara-hardware-enabled-verifying-responsible-ai/"
    },
    {
      "id": "S-0002",
      "title": "Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment",
      "authors": "M. Baker et al.",
      "year": 2025,
      "url": "https://www.rand.org/pubs/working_papers/WRA4077-1.html",
      "path": "/sources/baker-verifying-international-agreements-ai/"
    },
    {
      "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-1408",
      "title": "TSMC most definitely has a golden record of all AI chips it made",
      "authors": "N. Cankaya",
      "year": 2025,
      "url": "https://nacicankaya.substack.com/p/tsmc-most-definitely-has-a-golden",
      "path": "/sources/cankaya-tsmc-golden-record/"
    },
    {
      "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/"
    },
    {
      "id": "S-1410",
      "title": "Covert AI Projects",
      "authors": "B. Halstead & T. Larsen",
      "year": 2026,
      "url": "https://ai-2040.com/supplements/covert-ai-projects",
      "path": "/sources/halstead-covert-ai-projects/"
    }
  ]
}