{
  "schema_version": "1.3",
  "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0023,M-0002&implementations=M-0002:I-0012",
  "data_generated": "2026-10-09",
  "definitions": {
    "methodology": "https://trustbutveri.fyi/about/methodology/",
    "readiness": "https://trustbutveri.fyi/about/readiness/",
    "filters": [
      {
        "id": "prover",
        "label": "Prover",
        "question": "How far can the party being checked be trusted?",
        "options": [
          {
            "value": "cooperative",
            "label": "Cooperative"
          },
          {
            "value": "semi-trusted",
            "label": "Semi-trusted"
          },
          {
            "value": "adversarial",
            "label": "Adversarial"
          }
        ],
        "rule": "Keeps mechanisms whose threat model holds against at least this prover. Adversarial is the strongest assumption.",
        "about": "The prover is the party being checked. Semi-trusted designs rely on part of its stack: usually the chip vendor's hardware root of trust, its firmware or counters, or its supply-chain records. Adversarial designs aim to hold even if it cheats wherever the checks allow, within their stated assumptions."
      },
      {
        "id": "onsite",
        "label": "Verifier devices on site",
        "question": "May the verifier install its own hardware at the prover's sites?",
        "options": [
          {
            "value": "no",
            "label": "Not allowed"
          }
        ],
        "rule": "\"Not allowed\" removes mechanisms that need a retrofit device, such as a network tap or a sealed sensor.",
        "about": "Some mechanisms need a device the verifier owns or trusts at the prover's facility, such as a network tap, a bandwidth limiter or a sealed sensor. Choose Not allowed when the setting rules that out. Inspectors are not covered."
      },
      {
        "id": "coop",
        "label": "Prover cooperation",
        "question": "How much must the prover take part?",
        "options": [
          {
            "value": "partial",
            "label": "Partial at most"
          },
          {
            "value": "none",
            "label": "Not required"
          }
        ],
        "rule": "\"Partial at most\" removes mechanisms that need the prover's active participation. \"Not required\" keeps only those that work without it.",
        "about": "Required: the prover takes part, for example by logging requests, producing proofs or opening records. Partial: some access, such as installing a device. Not required: works from outside, such as satellite imagery."
      },
      {
        "id": "chips",
        "label": "Chips",
        "question": "May the proposal depend on new chip designs?",
        "options": [
          {
            "value": "existing",
            "label": "Existing chips only"
          }
        ],
        "rule": "\"Existing chips only\" removes mechanisms that need changes to future chip designs.",
        "about": "New chip features take years to reach a deployed fleet and cover only chips made after they ship. Mechanisms that use shipping features, such as trusted execution environments or performance counters, stay."
      },
      {
        "id": "ready",
        "label": "Minimum development status",
        "question": "Development status",
        "options": [
          {
            "value": "R1",
            "label": "Proposed"
          },
          {
            "value": "R2",
            "label": "Research demonstration"
          },
          {
            "value": "R3",
            "label": "Operational use"
          },
          {
            "value": "R4",
            "label": "Legacy independent-evaluation filter",
            "legacy": true
          }
        ],
        "rule": "Keeps mechanisms whose readiness level is at least this one.",
        "about": "A level describes the public evidence for a mechanism's stated use, not its cost or feasibility. R3 can still have open critical flaws."
      },
      {
        "id": "tested",
        "label": "Attack testing",
        "question": "How hard has each mechanism been attacked in public?",
        "options": [
          {
            "value": "analysis",
            "label": "Published analysis"
          },
          {
            "value": "red-teamed",
            "label": "Red-teamed"
          },
          {
            "value": "independent-red-team",
            "label": "Independent red-team"
          }
        ],
        "rule": "Keeps mechanisms whose strongest published attack testing is at least this.",
        "about": "The strongest published attempt to break the mechanism for its verification use: a security analysis, red-teaming by its developers or collaborators, or a red team independent of them."
      },
      {
        "id": "hide",
        "label": "Keep hidden from the verifier",
        "question": "What must the verifier never see?",
        "options": [
          {
            "value": "weights",
            "label": "Model weights"
          },
          {
            "value": "io",
            "label": "Inputs and outputs"
          },
          {
            "value": "training",
            "label": "Training data"
          }
        ],
        "rule": "Removes mechanisms that show the asset to the verifier. Conditional or unspecified exposure stays with a note and needs checking against the privacy requirement.",
        "about": "Model weights: the checked model's parameters. Inputs and outputs: the requests a deployed model serves and its responses. Training data: what a model was trained on. Each mechanism's exposure is the editors' reading of its record: shown, depends on the design (kept, with a note), hidden, not involved, or unspecified for a selected implementation. Code and configuration are not covered yet."
      }
    ],
    "exposure": "For model weights, inputs and outputs, and training data. This is the editors' reading of each mechanism's record (its threat model, how it works and its limitations), not a field of the record. Shown: the verifier sees it. Depends: on the design or variant, or the verifier sees only samples. Hidden: the verifier sees only commitments, hashes, proofs or results. Not involved: the record does not handle it. Unspecified: the selected implementation has no asset-specific assessment here.",
    "claim_status": {
      "addressed": "A mechanism in the proposal is aimed at this claim and is not excluded by the filters.",
      "partly-addressed": "Only supporting mechanisms, or mechanisms aimed at it that the filters exclude.",
      "unaddressed": "No mechanism in the proposal addresses this claim."
    },
    "finding_classification": {
      "failure": {
        "label": "Known failures",
        "singular": "Known failure",
        "anchor": "known-flaws"
      },
      "scope-limitation": {
        "label": "Scope limitations",
        "singular": "Scope limitation",
        "anchor": "scope-limitations"
      },
      "open-question": {
        "label": "Open questions",
        "singular": "Open question",
        "anchor": "open-questions"
      }
    },
    "finding_scope": "Evidence scope describes where a finding was demonstrated; it does not establish applicability to every implementation in the mechanism family.",
    "claim_finding_scope": "open_critical_findings names active failures on the assessed records; open_critical_context names conditional family failures whose implementation applicability is unassessed.",
    "legacy_status": "The status field retains covered/partial/none for compatibility. It names claim links, never successful verification. Use claim_status and status_label for presentation."
  },
  "filters": {
    "prover": "",
    "onsite": "",
    "coop": "",
    "chips": "",
    "ready": "",
    "tested": "",
    "hide": []
  },
  "mechanisms_passing_filters": 25,
  "claims": [],
  "mechanisms": [
    {
      "id": "M-0023",
      "title": "Safeguard attestation",
      "url": "https://trustbutveri.fyi/mechanisms/safeguard-attestation/",
      "assessment_record": {
        "id": "M-0023",
        "title": "Safeguard attestation",
        "url": "https://trustbutveri.fyi/mechanisms/safeguard-attestation/"
      },
      "finding_counts": {
        "failure": 2,
        "scope_limitation": 3,
        "open_question": 0,
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 0
        }
      },
      "selected_implementation": null,
      "readiness": {
        "level": "R2",
        "scope": "attesting that a declared safeguard mediated a service's responses",
        "confidence": "low",
        "evidence": [
          "S-1500",
          "S-1501",
          "S-3362",
          "S-0012",
          "S-1503",
          "S-1504",
          "S-1202",
          "S-3126"
        ]
      },
      "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": 4,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1500",
              "S-1501"
            ]
          },
          {
            "n": 5,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "inherited",
            "sources": [
              "S-1202",
              "S-3126",
              "S-1210",
              "S-1212",
              "S-1213",
              "S-0012",
              "S-0014",
              "S-1500",
              "S-0018"
            ],
            "related_finding": {
              "record": "M-0008",
              "flaw": 1
            }
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 0
        }
      },
      "assessed_properties": {
        "threat_model": "semi-trusted",
        "hardware_requirement": "existing-features",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "partial",
        "io": "partial",
        "training": "none",
        "note": "The enclave route signs hashes of the safeguard, request and response; a low-trust design has the verifier re-run and screen sampled requests itself."
      },
      "family_finding_context": [],
      "filter_issues": []
    },
    {
      "id": "M-0002",
      "title": "Deterministic and bit-exact inference",
      "url": "https://trustbutveri.fyi/mechanisms/deterministic-inference/",
      "assessment_record": {
        "id": "I-0012",
        "title": "Low-trust AI compute verification system overview",
        "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
      },
      "finding_counts": {
        "failure": 1,
        "scope_limitation": 1,
        "open_question": 1,
        "open_failures": {
          "critical": 0,
          "significant": 0,
          "minor": 1
        }
      },
      "selected_implementation": {
        "id": "I-0012",
        "title": "Low-trust AI compute verification system overview",
        "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
      },
      "readiness": {
        "level": "R1",
        "scope": "screening challenged records to show declared inference compute is not training",
        "confidence": "medium",
        "evidence": [
          "S-0018",
          "S-1300"
        ]
      },
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 2,
            "severity": "minor",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-0018"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 0,
          "minor": 1
        }
      },
      "assessed_properties": {
        "threat_model": "adversarial",
        "hardware_requirement": "retrofit-device",
        "prover_cooperation": "required",
        "adversarial_evaluation": "analysis"
      },
      "claims": [],
      "exposure": {
        "weights": "unknown",
        "io": "unknown",
        "training": "unknown",
        "note": "This Explorer has no asset-specific exposure assessment for this implementation. Check its source and deployment assumptions.",
        "sources": []
      },
      "family_finding_context": [
        {
          "n": 1,
          "historical": false,
          "title": "Some kernels remain genuinely nondeterministic",
          "classification": "scope-limitation",
          "kind": "open-question",
          "severity": "minor",
          "status": "open",
          "evidence_scope": null,
          "scope_note": null,
          "related_finding": null,
          "description": "The bit-exact work separates kernels that are deterministic but not batch-invariant from truly nondeterministic ones that use atomic functions. Some integer de-quantization kernels use atomic additions and remain nondeterministic, so exact replay needs backends that avoid them.",
          "response": null,
          "sources": [
            "S-0020"
          ],
          "record": "M-0002",
          "represented_by": []
        },
        {
          "n": 2,
          "historical": false,
          "title": "Cross-hardware replay relies on reverse-engineered, closed behaviour",
          "classification": "scope-limitation",
          "kind": "open-question",
          "severity": "significant",
          "status": "open",
          "evidence_scope": null,
          "scope_note": null,
          "related_finding": null,
          "description": "Emulating one GPU's rounding on another requires reverse-engineering tensor-core arithmetic and modelling proprietary kernel choices. Hawkeye covers a subset of NVIDIA architectures and states that attention and other higher-level operations need further reverse engineering. For the bit-exact emulator, a proprietary Hopper kernel family is an open edge case.",
          "response": null,
          "sources": [
            "S-1010",
            "S-0020"
          ],
          "record": "M-0002",
          "represented_by": []
        }
      ],
      "filter_issues": []
    }
  ],
  "strengths": {
    "covered": [],
    "production": [],
    "operationalUse": [],
    "adversarial": [
      "M-0002"
    ],
    "noNewHardware": [
      "M-0023"
    ],
    "mitigated": [],
    "notCounted": []
  },
  "properties": {
    "covered": [],
    "production": [],
    "operationalUse": [],
    "adversarial": [
      "M-0002"
    ],
    "noNewHardware": [
      "M-0023"
    ],
    "mitigated": [],
    "notCounted": []
  },
  "attack_testing": [
    {
      "id": "M-0023",
      "record": "M-0023",
      "evaluation": "analysis",
      "in_setting": true
    },
    {
      "id": "M-0002",
      "record": "I-0012",
      "evaluation": "analysis",
      "in_setting": true
    }
  ],
  "selected_implementations": {
    "M-0002": "I-0012"
  },
  "weaknesses": {
    "gaps": [],
    "excluded": [],
    "unlinked": [],
    "critical": [],
    "significant": [
      {
        "mech": "M-0023",
        "n": 4,
        "historical": false,
        "title": "Components outside the attested boundary",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "In the proof-of-guardrail experiments, the guardrail model and the agent's backend model were both reached through external APIs, and the authors leave the decision to trust those APIs to the verifier. The measured wrapper must also have no vulnerability that lets the unmeasured agent bypass the guardrail, for example by executing arbitrary commands inside the enclave. The code's README states that the enclave does not currently restrict the agent's arbitrary command execution, which could be used to bypass guardrails.",
        "response": null,
        "sources": [
          "S-1500",
          "S-1501"
        ]
      },
      {
        "mech": "M-0023",
        "n": 5,
        "historical": false,
        "title": "Memory-bus interposition extracts attestation keys and forges attestations",
        "classification": "failure",
        "kind": "demonstrated-attack",
        "severity": "significant",
        "status": "open",
        "evidence_scope": "inherited",
        "scope_note": "Applies to variants using the affected Intel or AMD trust roots. PAL*M excludes physical attacks. A TDX-backed safeguard claim against a physical host attacker would be defeated, but these studies do not demonstrate a break of the AWS Nitro proof-of-guardrail prototype or of verifier-side recomputation.",
        "related_finding": {
          "record": "M-0008",
          "flaw": 1
        },
        "description": "The TEE findings cover DDR5 attacks on Intel TDX, the H100 relay demonstration, DDR4 attacks on AMD SEV-SNP, and software-only SEV-SNP forgery before AMD's fixes. These are inherited hardware limits; a governance analysis explains why physical access matters in a treaty setting.",
        "response": "Intel and AMD place the physical attack class outside their threat models, according to the researchers. AMD reports firmware fixes for RMPocalypse.",
        "sources": [
          "S-1202",
          "S-3126",
          "S-1210",
          "S-1212",
          "S-1213",
          "S-0012",
          "S-0014",
          "S-1500",
          "S-0018"
        ],
        "helps": [
          {
            "by": "M-0009",
            "how": "A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically."
          }
        ]
      }
    ],
    "criticalMechanisms": [],
    "significantMechanisms": [
      "M-0023"
    ],
    "familyContext": [
      {
        "id": "M-0002",
        "implementation": "I-0012",
        "flaws": [
          {
            "n": 1,
            "historical": false,
            "title": "Some kernels remain genuinely nondeterministic",
            "classification": "scope-limitation",
            "kind": "open-question",
            "severity": "minor",
            "status": "open",
            "evidence_scope": null,
            "scope_note": null,
            "related_finding": null,
            "description": "The bit-exact work separates kernels that are deterministic but not batch-invariant from truly nondeterministic ones that use atomic functions. Some integer de-quantization kernels use atomic additions and remain nondeterministic, so exact replay needs backends that avoid them.",
            "response": null,
            "sources": [
              "S-0020"
            ],
            "record": "M-0002",
            "represented_by": []
          },
          {
            "n": 2,
            "historical": false,
            "title": "Cross-hardware replay relies on reverse-engineered, closed behaviour",
            "classification": "scope-limitation",
            "kind": "open-question",
            "severity": "significant",
            "status": "open",
            "evidence_scope": null,
            "scope_note": null,
            "related_finding": null,
            "description": "Emulating one GPU's rounding on another requires reverse-engineering tensor-core arithmetic and modelling proprietary kernel choices. Hawkeye covers a subset of NVIDIA architectures and states that attention and other higher-level operations need further reverse engineering. For the bit-exact emulator, a proprietary Hopper kernel family is an open edge case.",
            "response": null,
            "sources": [
              "S-1010",
              "S-0020"
            ],
            "record": "M-0002",
            "represented_by": []
          }
        ]
      }
    ],
    "scopeLimitations": [
      {
        "mech": "M-0023",
        "n": 1,
        "historical": false,
        "title": "Attestation shows a safeguard ran, not that it is effective",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Proof of guardrail ensures that the guardrail executed, but the guardrail can still err or be jailbroken. Because the guardrail must be open source, a malicious developer can attack it with jailbreaks while still presenting a valid proof. In the authors' evaluation, Llama Guard 3 reached an F1 score of 0.56 on the unsafe class of the ToxicChat dataset. The authors state that proof of guardrail should not be interpreted or advertised as proof of safety.",
        "response": null,
        "sources": [
          "S-1500"
        ]
      },
      {
        "mech": "M-0023",
        "n": 2,
        "historical": false,
        "title": "Selective attestation leaves traffic uncovered",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Attestations are issued per response. In the prototype, the agent offers them when it receives high-stakes questions, so nothing shows that unattested traffic went through the same path. PAL*M's authors note that a prover could cherry-pick favourable executions, and suggest verifier-published nonces or requesting only session-level proofs. A governance analysis notes that auditors also need assurance that all activity is accounted for, since a host could start a second confidential virtual machine that bypasses monitoring.",
        "response": null,
        "sources": [
          "S-1500",
          "S-0012",
          "S-0014"
        ],
        "helps": [
          {
            "by": "M-0010",
            "how": "On-chip counters are a proposed route to evidence about everything a chip runs, including a second virtual machine that skips the safeguard."
          }
        ]
      },
      {
        "mech": "M-0023",
        "n": 3,
        "historical": false,
        "title": "Measurements may omit behaviour-relevant configuration or runtime changes",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Every component that influences inference behaviour must be covered by the launch measurement, including feature flags, environment variables and invocation arguments. A launch measurement also does not show that a program keeps running as measured if the kernel is later compromised.",
        "response": null,
        "sources": [
          "S-0014"
        ]
      },
      {
        "mech": "M-0002",
        "n": 1,
        "historical": false,
        "title": "Mismatches cannot be attributed to cheating or error",
        "classification": "scope-limitation",
        "kind": "theoretical-argument",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "A failed hash or replay does not show whether it came from an evasion attempt, a random bit flip or an evaluation error. The author notes that if detected anomalies can plausibly be waved off as malfunctions, deterrence becomes less effective, so the parties need an agreed escalation procedure that ends in attribution.",
        "response": null,
        "sources": [
          "S-0018"
        ],
        "record": "I-0012"
      }
    ],
    "openQuestions": [
      {
        "mech": "M-0002",
        "n": 3,
        "historical": false,
        "title": "Inspector agents may be manipulable",
        "classification": "open-question",
        "kind": "open-question",
        "severity": "significant",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "Automated compliance screening with LLM-based inspector agents must resist prompt-injection attacks. Adversarially trained systems might hide malicious actions with steganography, which makes backdoor detection an open problem.",
        "response": null,
        "sources": [
          "S-0018"
        ],
        "record": "I-0012"
      }
    ],
    "minor": 1,
    "minorFindings": [
      {
        "mech": "M-0002",
        "n": 2,
        "historical": false,
        "title": "Deliberate faults leak a bit each",
        "classification": "failure",
        "kind": "theoretical-argument",
        "severity": "minor",
        "status": "open",
        "evidence_scope": null,
        "scope_note": null,
        "related_finding": null,
        "description": "A malicious device can leak one bit by deliberately outputting a wrong result, which blocks a disclosure when the cross-comparison fails. The design therefore needs a pre-agreed budget of tolerated faults.",
        "response": null,
        "sources": [
          "S-0018"
        ],
        "record": "I-0012"
      }
    ],
    "minorBy": [
      {
        "id": "M-0002",
        "n": 1
      }
    ],
    "notDemonstrated": [
      "M-0002"
    ],
    "newChip": []
  },
  "findings": [
    {
      "mech": "M-0023",
      "record": "M-0023",
      "n": 1,
      "historical": false,
      "title": "Attestation shows a safeguard ran, not that it is effective",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Proof of guardrail ensures that the guardrail executed, but the guardrail can still err or be jailbroken. Because the guardrail must be open source, a malicious developer can attack it with jailbreaks while still presenting a valid proof. In the authors' evaluation, Llama Guard 3 reached an F1 score of 0.56 on the unsafe class of the ToxicChat dataset. The authors state that proof of guardrail should not be interpreted or advertised as proof of safety.",
      "response": null,
      "sources": [
        "S-1500"
      ]
    },
    {
      "mech": "M-0023",
      "record": "M-0023",
      "n": 2,
      "historical": false,
      "title": "Selective attestation leaves traffic uncovered",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Attestations are issued per response. In the prototype, the agent offers them when it receives high-stakes questions, so nothing shows that unattested traffic went through the same path. PAL*M's authors note that a prover could cherry-pick favourable executions, and suggest verifier-published nonces or requesting only session-level proofs. A governance analysis notes that auditors also need assurance that all activity is accounted for, since a host could start a second confidential virtual machine that bypasses monitoring.",
      "response": null,
      "sources": [
        "S-1500",
        "S-0012",
        "S-0014"
      ],
      "helps": [
        {
          "by": "M-0010",
          "how": "On-chip counters are a proposed route to evidence about everything a chip runs, including a second virtual machine that skips the safeguard."
        }
      ]
    },
    {
      "mech": "M-0023",
      "record": "M-0023",
      "n": 3,
      "historical": false,
      "title": "Measurements may omit behaviour-relevant configuration or runtime changes",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Every component that influences inference behaviour must be covered by the launch measurement, including feature flags, environment variables and invocation arguments. A launch measurement also does not show that a program keeps running as measured if the kernel is later compromised.",
      "response": null,
      "sources": [
        "S-0014"
      ]
    },
    {
      "mech": "M-0023",
      "record": "M-0023",
      "n": 4,
      "historical": false,
      "title": "Components outside the attested boundary",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "In the proof-of-guardrail experiments, the guardrail model and the agent's backend model were both reached through external APIs, and the authors leave the decision to trust those APIs to the verifier. The measured wrapper must also have no vulnerability that lets the unmeasured agent bypass the guardrail, for example by executing arbitrary commands inside the enclave. The code's README states that the enclave does not currently restrict the agent's arbitrary command execution, which could be used to bypass guardrails.",
      "response": null,
      "sources": [
        "S-1500",
        "S-1501"
      ]
    },
    {
      "mech": "M-0023",
      "record": "M-0023",
      "n": 5,
      "historical": false,
      "title": "Memory-bus interposition extracts attestation keys and forges attestations",
      "classification": "failure",
      "kind": "demonstrated-attack",
      "severity": "significant",
      "status": "open",
      "evidence_scope": "inherited",
      "scope_note": "Applies to variants using the affected Intel or AMD trust roots. PAL*M excludes physical attacks. A TDX-backed safeguard claim against a physical host attacker would be defeated, but these studies do not demonstrate a break of the AWS Nitro proof-of-guardrail prototype or of verifier-side recomputation.",
      "related_finding": {
        "record": "M-0008",
        "flaw": 1
      },
      "description": "The TEE findings cover DDR5 attacks on Intel TDX, the H100 relay demonstration, DDR4 attacks on AMD SEV-SNP, and software-only SEV-SNP forgery before AMD's fixes. These are inherited hardware limits; a governance analysis explains why physical access matters in a treaty setting.",
      "response": "Intel and AMD place the physical attack class outside their threat models, according to the researchers. AMD reports firmware fixes for RMPocalypse.",
      "sources": [
        "S-1202",
        "S-3126",
        "S-1210",
        "S-1212",
        "S-1213",
        "S-0012",
        "S-0014",
        "S-1500",
        "S-0018"
      ],
      "helps": [
        {
          "by": "M-0009",
          "how": "A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically."
        }
      ]
    },
    {
      "mech": "M-0002",
      "record": "I-0012",
      "n": 1,
      "historical": false,
      "title": "Mismatches cannot be attributed to cheating or error",
      "classification": "scope-limitation",
      "kind": "theoretical-argument",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "A failed hash or replay does not show whether it came from an evasion attempt, a random bit flip or an evaluation error. The author notes that if detected anomalies can plausibly be waved off as malfunctions, deterrence becomes less effective, so the parties need an agreed escalation procedure that ends in attribution.",
      "response": null,
      "sources": [
        "S-0018"
      ]
    },
    {
      "mech": "M-0002",
      "record": "I-0012",
      "n": 2,
      "historical": false,
      "title": "Deliberate faults leak a bit each",
      "classification": "failure",
      "kind": "theoretical-argument",
      "severity": "minor",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "A malicious device can leak one bit by deliberately outputting a wrong result, which blocks a disclosure when the cross-comparison fails. The design therefore needs a pre-agreed budget of tolerated faults.",
      "response": null,
      "sources": [
        "S-0018"
      ]
    },
    {
      "mech": "M-0002",
      "record": "I-0012",
      "n": 3,
      "historical": false,
      "title": "Inspector agents may be manipulable",
      "classification": "open-question",
      "kind": "open-question",
      "severity": "significant",
      "status": "open",
      "evidence_scope": null,
      "scope_note": null,
      "related_finding": null,
      "description": "Automated compliance screening with LLM-based inspector agents must resist prompt-injection attacks. Adversarially trained systems might hide malicious actions with steganography, which makes backdoor detection an open problem.",
      "response": null,
      "sources": [
        "S-0018"
      ]
    }
  ],
  "possible_additions": [
    {
      "id": "M-0009",
      "title": "Hardware-enabled guarantees (flexHEG) and guarantee processors",
      "url": "https://trustbutveri.fyi/mechanisms/flexheg-guarantee-processors/",
      "readiness": "R1",
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1204",
              "S-0057"
            ]
          },
          {
            "n": 2,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1204"
            ]
          },
          {
            "n": 4,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1204"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 3,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "flaw",
          "mech": "M-0023",
          "n": 5,
          "title": "Memory-bus interposition extracts attestation keys and forges attestations",
          "severity": "significant",
          "how": "A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically."
        }
      ]
    },
    {
      "id": "M-0012",
      "title": "Hardware-attested weight binding",
      "url": "https://trustbutveri.fyi/mechanisms/model-identity-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": "inherited",
            "sources": [
              "S-1202",
              "S-1210",
              "S-1212",
              "S-1213",
              "S-1206",
              "S-0012"
            ],
            "related_finding": {
              "record": "M-0008",
              "flaw": 1
            }
          },
          {
            "n": 2,
            "severity": "significant",
            "status": "mitigated",
            "evidence_scope": "unassessed",
            "sources": [
              "S-0013",
              "S-0014"
            ]
          }
        ],
        "open_failures": {
          "critical": 1,
          "significant": 0,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0023",
          "text": "Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation."
        }
      ]
    },
    {
      "id": "M-0008",
      "title": "TEE remote attestation for AI workloads",
      "url": "https://trustbutveri.fyi/mechanisms/tee-remote-attestation/",
      "readiness": "R3",
      "development_status": {
        "code": "R3",
        "label": "Operational use",
        "short": "Operational use",
        "rank": 3,
        "legacy_code": "R3"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "independent-red-team",
          "label": "Published attack testing",
          "kind": "practical",
          "attribution": "Independent team"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "critical",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1202",
              "S-3126",
              "S-0012",
              "S-1206",
              "S-0014",
              "S-1210",
              "S-1212",
              "S-3127"
            ]
          },
          {
            "n": 2,
            "severity": "critical",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1210",
              "S-1211"
            ]
          },
          {
            "n": 3,
            "severity": "critical",
            "status": "mitigated",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1212",
              "S-1213",
              "S-3127",
              "S-3128"
            ]
          },
          {
            "n": 4,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-1202"
            ]
          },
          {
            "n": 5,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-0012",
              "S-0009",
              "S-0014",
              "S-3123",
              "S-3129"
            ]
          },
          {
            "n": 8,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "mechanism",
            "sources": [
              "S-0014",
              "S-0009",
              "S-3130",
              "S-3131"
            ]
          }
        ],
        "open_failures": {
          "critical": 2,
          "significant": 3,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0023",
          "text": "Frontier model inference typically needs several GPUs, GPU confidential computing is less mature than CPU support, and CPU inference, which an enclave prototype had to use, ran about 100 times slower than GPU inference."
        },
        {
          "kind": "blocker",
          "mech": "M-0023",
          "text": "Trust rests on a small number of hardware vendors, and a per-CPU Intel attestation key has been extracted by physical attack."
        }
      ]
    },
    {
      "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-0002",
          "text": "Tamper-evident, rapidly mass-manufacturable and retrofittable enclosures for side-channel defence are an open research question, and physical security against covert communication in every monitored data centre is challenging."
        }
      ]
    },
    {
      "id": "M-0016",
      "title": "Timed challenge-response and memory-occupation challenges",
      "url": "https://trustbutveri.fyi/mechanisms/timed-challenge-response/",
      "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": "disputed",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1308",
              "S-0074"
            ]
          },
          {
            "n": 2,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-0018"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 1,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0002",
          "text": "Distinguishing one server's DRAM contents from another's by challenge-response timing, and a general challenge-response protocol for diverse data types, are open."
        }
      ]
    },
    {
      "id": "M-0013",
      "title": "Network taps and certifiers",
      "url": "https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/",
      "readiness": "R1",
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [
          {
            "n": 1,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1300",
              "S-1507"
            ]
          },
          {
            "n": 4,
            "severity": "significant",
            "status": "open",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1312"
            ]
          },
          {
            "n": 6,
            "severity": "minor",
            "status": "mitigated",
            "evidence_scope": "unassessed",
            "sources": [
              "S-1300"
            ]
          }
        ],
        "open_failures": {
          "critical": 0,
          "significant": 2,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0002",
          "text": "Empirical feasibility of passive optical splitting at 53–112 GBaud under realistic conditions is an open question."
        }
      ]
    },
    {
      "id": "M-0022",
      "title": "Side-channel suppression for isolated facilities",
      "url": "https://trustbutveri.fyi/mechanisms/side-channel-suppression/",
      "readiness": "R1",
      "development_status": {
        "code": "R1",
        "label": "Proposed",
        "short": "Proposed",
        "rank": 1,
        "legacy_code": "R1"
      },
      "security_evidence": {
        "attack_testing": {
          "status": "analysis",
          "label": "Published security analysis",
          "kind": "analysis"
        },
        "independent_evaluation": {
          "status": "unassessed"
        },
        "formal_proof": {
          "status": "unassessed"
        },
        "deployment_assurance": {
          "status": "unassessed"
        },
        "legacy_evaluation_code": null,
        "scoped_findings": [],
        "open_failures": {
          "critical": 0,
          "significant": 0,
          "minor": 0
        }
      },
      "fits_filters": true,
      "filter_issues": [],
      "reasons": [
        {
          "kind": "blocker",
          "mech": "M-0002",
          "text": "A mass-manufacturable, good-enough side-channel defence, particularly power-line filtering, has not been constructed or red-teamed."
        }
      ]
    }
  ],
  "goal": null,
  "design": null,
  "dependencies": {
    "prerequisites": [
      {
        "id": "M-0008",
        "neededBy": [
          "M-0023"
        ]
      },
      {
        "id": "M-0012",
        "neededBy": [
          "M-0023"
        ]
      },
      {
        "id": "M-0013",
        "neededBy": [
          "M-0002"
        ]
      }
    ],
    "shared": [],
    "blockers": [
      {
        "mech": "M-0023",
        "n": 1,
        "historical": false,
        "text": "No published design shows that all of a provider's traffic passes through the attested safeguard path; current evidence covers individual attested responses.",
        "theme": "coverage-hidden-compute",
        "blocked_by": null,
        "sources": [
          "S-1500",
          "S-0014"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0023",
        "n": 2,
        "historical": false,
        "text": "Frontier model inference typically needs several GPUs, GPU confidential computing is less mature than CPU support, and CPU inference, which an enclave prototype had to use, ran about 100 times slower than GPU inference.",
        "theme": "performance-compatibility",
        "blocked_by": "M-0008",
        "sources": [
          "S-0014",
          "S-0009"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0023",
        "n": 3,
        "historical": false,
        "text": "Trust rests on a small number of hardware vendors, and a per-CPU Intel attestation key has been extracted by physical attack.",
        "theme": "hardware-trust",
        "blocked_by": "M-0008",
        "sources": [
          "S-0014",
          "S-1202"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0023",
        "n": 4,
        "historical": false,
        "text": "Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation.",
        "theme": "evidence-binding",
        "blocked_by": "M-0012",
        "sources": [
          "S-0009",
          "S-0013"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0023",
        "n": 5,
        "historical": false,
        "text": "No independent red-team or audit of a safeguard-attestation system has been published, and the available prototypes are described by their authors as proofs of concept that have not been stress-tested by a counterparty.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-1501",
          "S-1504"
        ],
        "inProposal": null
      },
      {
        "mech": "M-0002",
        "n": 1,
        "historical": false,
        "text": "Empirical feasibility of passive optical splitting at 53–112 GBaud under realistic conditions is an open question.",
        "theme": "performance-compatibility",
        "blocked_by": "M-0013",
        "sources": [
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0002",
        "n": 2,
        "historical": false,
        "text": "Exact replay needs complete hardware and software metadata, and the tolerable slowdown from emulation is an open question.",
        "theme": "performance-compatibility",
        "blocked_by": "M-0002",
        "sources": [
          "S-0018"
        ],
        "inProposal": true
      },
      {
        "mech": "M-0002",
        "n": 3,
        "historical": false,
        "text": "Tamper-evident, rapidly mass-manufacturable and retrofittable enclosures for side-channel defence are an open research question, and physical security against covert communication in every monitored data centre is challenging.",
        "theme": "hardware-trust",
        "blocked_by": "M-0017",
        "sources": [
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0002",
        "n": 4,
        "historical": false,
        "text": "A mass-manufacturable, good-enough side-channel defence, particularly power-line filtering, has not been constructed or red-teamed.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0022",
        "sources": [
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0002",
        "n": 5,
        "historical": false,
        "text": "Distinguishing one server's DRAM contents from another's by challenge-response timing, and a general challenge-response protocol for diverse data types, are open.",
        "theme": "coverage-hidden-compute",
        "blocked_by": "M-0016",
        "sources": [
          "S-0018"
        ],
        "inProposal": false
      },
      {
        "mech": "M-0002",
        "n": 6,
        "historical": false,
        "text": "The threat model is under-developed and needs input from cybersecurity and AI threat-modelling experts.",
        "theme": "adversarial-validation",
        "blocked_by": null,
        "sources": [
          "S-0018"
        ],
        "inProposal": null
      }
    ]
  },
  "exposure": {
    "weights": {
      "shown": [],
      "partial": [
        "M-0023"
      ],
      "hidden": [],
      "none": [],
      "unknown": [
        "M-0002"
      ]
    },
    "io": {
      "shown": [],
      "partial": [
        "M-0023"
      ],
      "hidden": [],
      "none": [],
      "unknown": [
        "M-0002"
      ]
    },
    "training": {
      "shown": [],
      "partial": [],
      "hidden": [],
      "none": [
        "M-0023"
      ],
      "unknown": [
        "M-0002"
      ]
    }
  },
  "implementations": [
    {
      "mechanism": "M-0023",
      "selected": null,
      "implementations": []
    },
    {
      "mechanism": "M-0002",
      "selected": {
        "id": "I-0012",
        "title": "Low-trust AI compute verification system overview",
        "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
      },
      "implementations": [
        {
          "id": "I-0016",
          "title": "Batch-invariant inference kernels (Thinking Machines)",
          "url": "https://trustbutveri.fyi/implementations/batch-invariant-inference-kernels/"
        },
        {
          "id": "I-0015",
          "title": "Verde and RepOps (Gensyn)",
          "url": "https://trustbutveri.fyi/implementations/gensyn-verde-repops/"
        },
        {
          "id": "I-0012",
          "title": "Low-trust AI compute verification system overview",
          "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
        }
      ]
    }
  ],
  "sources": [
    {
      "id": "S-1500",
      "title": "Proof-of-Guardrail in AI Agents and What (Not) to Trust from It",
      "authors": "X. Jin et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2603.05786",
      "path": "/sources/jin-proof-of-guardrail/"
    },
    {
      "id": "S-1501",
      "title": "Verifiable-ClawGuard: proof-of-guardrail reference code",
      "authors": "SaharaLabsAI",
      "year": 2026,
      "url": "https://github.com/SaharaLabsAI/Verifiable-ClawGuard",
      "path": "/sources/sahara-verifiable-clawguard-code/"
    },
    {
      "id": "S-3362",
      "title": "Safety Without Compromising on Privacy",
      "authors": "D. McCann-Sayles et al.",
      "year": 2026,
      "url": "https://tinfoil.sh/blog/2026-09-14-safety-without-compromising-privacy",
      "path": "/sources/tinfoil-safety-without-compromising-privacy/"
    },
    {
      "id": "S-0012",
      "title": "PAL*M: Property Attestation for Large Generative Models",
      "authors": "P. Chantasantitam et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2601.16199",
      "path": "/sources/chantasantitam-palm/"
    },
    {
      "id": "S-1503",
      "title": "Enabling Verifiably-Scoped Monitoring through Large Language Models and Trusted Compute",
      "authors": "B. Penchas et al.",
      "year": 2026,
      "url": "https://icml.cc/virtual/2026/78630",
      "path": "/sources/penchas-verifiably-scoped-monitoring/"
    },
    {
      "id": "S-1504",
      "title": "Auditor-in-a-Box: Tools for Third-Party Auditing",
      "authors": "R. Rinberg & B. Penchas",
      "year": 2026,
      "url": "https://www.lesswrong.com/posts/uWYk7MM9hAf9GEbGe/auditor-in-a-box-tools-for-third-party-auditing",
      "path": "/sources/rinberg-auditor-in-a-box/"
    },
    {
      "id": "S-1202",
      "title": "TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition",
      "authors": "J. Chuang et al.",
      "year": 2026,
      "url": "https://tee.fail/",
      "path": "/sources/chuang-tee-fail/"
    },
    {
      "id": "S-3126",
      "title": "DDRop: Active Memory Interposer Attacks on Confidential VMs by Dropping DDR5 Writes",
      "authors": "J. De Meulemeester et al.",
      "year": 2026,
      "url": "https://ddropattack.eu/",
      "path": "/sources/de-meulemeester-ddrop/"
    },
    {
      "id": "S-0014",
      "title": "On TEEs for Privacy-Preserving Monitoring in AI Governance",
      "authors": "Gloria Z",
      "year": 2026,
      "url": "https://techgov.intelligence.org/blog/on-tees-for-privacy-preserving-monitoring-in-ai-governance",
      "path": "/sources/zhao-tees-privacy-preserving-monitoring/"
    },
    {
      "id": "S-1210",
      "title": "Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing",
      "authors": "J. De Meulemeester et al.",
      "year": 2026,
      "url": "https://batteringram.eu/",
      "path": "/sources/de-meulemeester-battering-ram/"
    },
    {
      "id": "S-1212",
      "title": "RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP",
      "authors": "B. Schlüter & S. Shinde",
      "year": 2025,
      "url": "https://rmpocalypse.github.io/",
      "path": "/sources/schluter-rmpocalypse/"
    },
    {
      "id": "S-1213",
      "title": "SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020)",
      "authors": "AMD",
      "year": 2025,
      "url": "https://www.amd.com/en/resources/product-security/bulletin/amd-sb-3020.html",
      "path": "/sources/amd-sb-3020-rmp-initialization/"
    },
    {
      "id": "S-0018",
      "title": "A System Overview for Near-Term, Low-Trust AI Compute Verification",
      "authors": "N. Cankaya",
      "year": 2026,
      "url": "https://intelligence.org/wp-content/uploads/2026/06/A-system-overview-for-near-term-low-trust-AI-compute-verification.pdf",
      "path": "/sources/cankaya-system-overview-low-trust-compute-verification/"
    },
    {
      "id": "S-1300",
      "title": "Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors",
      "authors": "N. Cankaya et al.",
      "year": 2026,
      "url": "https://arxiv.org/abs/2606.10724",
      "path": "/sources/cankaya-fingerprinting-ai-cluster-io/"
    },
    {
      "id": "S-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-1010",
      "title": "Hawkeye: Reproducing GPU-Level Non-Determinism",
      "authors": "E. Badash et al.",
      "year": 2026,
      "url": "https://proceedings.mlsys.org/paper_files/paper/2026/hash/e217c271a57c365a246b0ad39e668ba8-Abstract-Conference.html",
      "path": "/sources/badash-hawkeye/"
    },
    {
      "id": "S-0009",
      "title": "Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments",
      "authors": "C. Schnabl et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2506.23706",
      "path": "/sources/schnabl-attestable-audits/"
    },
    {
      "id": "S-0013",
      "title": "How Tinfoil Proves Exactly What Model Is Running",
      "authors": "Tinfoil Team",
      "year": 2026,
      "url": "https://tinfoil.sh/blog/2026-02-03-proving-model-identity",
      "path": "/sources/tinfoil-proving-model-identity/"
    }
  ]
}