{ "schema_version": "1.3", "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0012,M-0017,M-0013,M-0001", "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-0012", "title": "Hardware-attested weight binding", "url": "https://trustbutveri.fyi/mechanisms/model-identity-attestation/", "assessment_record": { "id": "M-0012", "title": "Hardware-attested weight binding", "url": "https://trustbutveri.fyi/mechanisms/model-identity-attestation/" }, "finding_counts": { "failure": 2, "scope_limitation": 1, "open_question": 0, "open_failures": { "critical": 1, "significant": 0, "minor": 0 } }, "selected_implementation": null, "readiness": { "level": "R3", "scope": "hardware-attested weight binding showing users that a service runs its committed weights", "confidence": "medium", "evidence": [ "S-0013", "S-0012", "S-1206", "S-1207", "S-1208", "S-1209", "S-1202" ] }, "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 } }, "assessed_properties": { "threat_model": "semi-trusted", "hardware_requirement": "existing-features", "prover_cooperation": "required", "adversarial_evaluation": "independent-red-team" }, "claims": [], "exposure": { "weights": "hidden", "io": "unknown", "training": "none", "note": "Verifiers check a hash commitment to the weights, carried in a hardware attestation, and need no access to the weights themselves. The mechanism does not specify whether prompts and outputs are disclosed to a verifier. It involves no training data.", "sources": [ "S-0013", "S-0012", "S-0009" ] }, "family_finding_context": [], "filter_issues": [] }, { "id": "M-0017", "title": "Tamper evidence for verifier devices", "url": "https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/", "assessment_record": { "id": "M-0017", "title": "Tamper evidence for verifier devices", "url": "https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/" }, "finding_counts": { "failure": 2, "scope_limitation": 1, "open_question": 0, "open_failures": { "critical": 0, "significant": 2, "minor": 0 } }, "selected_implementation": null, "readiness": { "level": "R2", "scope": "detecting probing of proposed verifier hardware, using server and electronics prototypes as evidence", "confidence": "medium", "evidence": [ "S-0052", "S-1315", "S-0051", "S-0050", "S-3262", "S-1316", "S-0018" ] }, "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 } }, "assessed_properties": { "threat_model": "adversarial", "hardware_requirement": "retrofit-device", "prover_cooperation": "partial", "adversarial_evaluation": "analysis" }, "claims": [], "exposure": { "weights": "none", "io": "none", "training": "none", "note": "Protects verifier devices; it does not handle model data." }, "family_finding_context": [], "filter_issues": [] }, { "id": "M-0013", "title": "Network taps and certifiers", "url": "https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/", "assessment_record": { "id": "M-0013", "title": "Network taps and certifiers", "url": "https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/" }, "finding_counts": { "failure": 3, "scope_limitation": 3, "open_question": 0, "open_failures": { "critical": 0, "significant": 2, "minor": 0 } }, "selected_implementation": null, "readiness": { "level": "R1", "scope": "committing a complete record of cluster traffic, so declared inference can be checked", "confidence": "medium", "evidence": [ "S-1300", "S-0031", "S-0018", "S-0067", "S-1312", "S-1007", "S-1319", "S-1320" ] }, "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 } }, "assessed_properties": { "threat_model": "adversarial", "hardware_requirement": "retrofit-device", "prover_cooperation": "required", "adversarial_evaluation": "analysis" }, "claims": [], "exposure": { "weights": "partial", "io": "partial", "training": "partial", "note": "Only hashes leave the site; records picked for a challenge are opened for replay at a verification facility." }, "family_finding_context": [], "filter_issues": [] }, { "id": "M-0001", "title": "Sampled inference recomputation", "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/", "assessment_record": { "id": "M-0001", "title": "Sampled inference recomputation", "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/" }, "finding_counts": { "failure": 3, "scope_limitation": 1, "open_question": 0, "open_failures": { "critical": 0, "significant": 2, "minor": 1 } }, "selected_implementation": null, "readiness": { "level": "R3", "scope": "checking untrusted workers' activations against the declared model, prompt and precision", "confidence": "low", "evidence": [ "S-0015", "S-0016", "S-1000", "S-1001", "S-1003", "S-1005", "S-1006", "S-1008", "S-1507", "S-3000", "S-3001" ] }, "development_status": { "code": "R3", "label": "Operational use", "short": "Operational use", "rank": 3, "legacy_code": "R3" }, "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-0020", "S-0015", "S-1507" ] }, { "n": 3, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1000", "S-0016" ] }, { "n": 4, "severity": "minor", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-0016" ] } ], "open_failures": { "critical": 0, "significant": 2, "minor": 1 } }, "assessed_properties": { "threat_model": "adversarial", "hardware_requirement": "none", "prover_cooperation": "required", "adversarial_evaluation": "analysis" }, "claims": [], "exposure": { "weights": "partial", "io": "partial", "training": "none", "note": "Recomputation needs the weights and sampled requests inside the checking environment. For closed models, the record describes a trusted, confidential environment; disclosure to the verifier depends on that boundary.", "sources": [ "S-0016", "S-0017", "S-0018" ] }, "family_finding_context": [], "filter_issues": [] } ], "strengths": { "covered": [], "production": [ "M-0012", "M-0001" ], "operationalUse": [ "M-0012", "M-0001" ], "adversarial": [ "M-0017", "M-0013", "M-0001" ], "noNewHardware": [ "M-0012", "M-0001" ], "mitigated": [ { "mech": "M-0012", "n": 2, "historical": false, "title": "Launch-state attestation does not by itself cover weights loaded later", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "mitigated", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Attestation measures launch state, and weights are read from disk after boot. A signature checked at load time does not stop a malicious hypervisor from altering the disk afterwards. Tinfoil reports mitigating this with dm-verity checks on every read. Unmeasured runtime configuration remains a general risk.", "response": null, "sources": [ "S-0013", "S-0014" ] }, { "mech": "M-0013", "n": 6, "historical": false, "title": "Verifier dictionary attacks on hashes", "classification": "failure", "kind": "theoretical-argument", "severity": "minor", "status": "mitigated", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Hashes of very short outputs could be brute-forced by the verifier. The paper recommends hashing at least 5 tokens together, or at least 10 if the attacker filters for likely tokens.", "response": null, "sources": [ "S-1300" ] } ], "notCounted": [] }, "properties": { "covered": [], "production": [ "M-0012", "M-0001" ], "operationalUse": [ "M-0012", "M-0001" ], "adversarial": [ "M-0017", "M-0013", "M-0001" ], "noNewHardware": [ "M-0012", "M-0001" ], "mitigated": [ { "mech": "M-0012", "n": 2, "historical": false, "title": "Launch-state attestation does not by itself cover weights loaded later", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "mitigated", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Attestation measures launch state, and weights are read from disk after boot. A signature checked at load time does not stop a malicious hypervisor from altering the disk afterwards. Tinfoil reports mitigating this with dm-verity checks on every read. Unmeasured runtime configuration remains a general risk.", "response": null, "sources": [ "S-0013", "S-0014" ] }, { "mech": "M-0013", "n": 6, "historical": false, "title": "Verifier dictionary attacks on hashes", "classification": "failure", "kind": "theoretical-argument", "severity": "minor", "status": "mitigated", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Hashes of very short outputs could be brute-forced by the verifier. The paper recommends hashing at least 5 tokens together, or at least 10 if the attacker filters for likely tokens.", "response": null, "sources": [ "S-1300" ] } ], "notCounted": [] }, "attack_testing": [ { "id": "M-0012", "record": "M-0012", "evaluation": "independent-red-team", "in_setting": true }, { "id": "M-0017", "record": "M-0017", "evaluation": "analysis", "in_setting": true }, { "id": "M-0013", "record": "M-0013", "evaluation": "analysis", "in_setting": true }, { "id": "M-0001", "record": "M-0001", "evaluation": "analysis", "in_setting": true } ], "selected_implementations": {}, "weaknesses": { "gaps": [], "excluded": [], "unlinked": [], "critical": [ { "mech": "M-0012", "n": 1, "historical": false, "title": "Underlying attestation can be forged or relayed", "classification": "failure", "kind": "demonstrated-attack", "severity": "critical", "status": "open", "evidence_scope": "inherited", "scope_note": "Critical for weight binding against an operator with physical access to affected hardware, or with control of the hypervisor on an AMD SEV-SNP platform without AMD's fixes. PAL*M excludes physical attacks, and Tinfoil acknowledges this boundary.", "related_finding": { "record": "M-0008", "flaw": 1 }, "description": "The enclave route inherits the platform-specific TEE attestation failures. Intel TDX forgery and H100 relay were demonstrated with physical access and host control. Battering RAM defeated AMD SEV-SNP attestation on DDR4 servers; RMPocalypse did so from malicious host software on platforms without AMD's fixes. These demonstrate failures of the trust roots, not of each model-commitment protocol.", "response": "The TEE.fail authors report that physical interposer attacks are outside Intel's and AMD's threat models. AMD reports fixes for RMPocalypse.", "sources": [ "S-1202", "S-1210", "S-1212", "S-1213", "S-1206", "S-0012" ], "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." } ] } ], "significant": [ { "mech": "M-0017", "n": 1, "historical": false, "title": "Seals are often defeated with simple methods", "classification": "failure", "kind": "demonstrated-attack", "severity": "significant", "status": "open", "evidence_scope": "mechanism", "scope_note": "Published defeats of general security seals. They warn about proposed verifier-device seals, but do not demonstrate defeat of an AI verification enclosure or sensor.", "related_finding": null, "description": "In 1996 a Los Alamos vulnerability assessment defeated all 94 security seals it examined, with 132 defeats in total, using rapid, inexpensive, low-tech methods. It found that seal cost did not predict security. In 2001 Johnston reported that high-tech seals are often easier to defeat than low-tech ones.", "response": null, "sources": [ "S-1317", "S-1318" ] }, { "mech": "M-0017", "n": 3, "historical": false, "title": "Attack classes outside published models", "classification": "failure", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": "mechanism", "scope_note": "The radio compensation result is emulated using measured channel data under a known-reference attacker model. It is not a physical bypass demonstration against an AI verifier enclosure.", "related_finding": null, "description": "The authors of the batteryless cover say they cannot assess chemical-solvent attacks, which exceed their expertise, and deem cover removal impractical. Anti-Tamper Radio's reference can drift as the environment or measurement system ages; the authors suggest gradually renewing the reference. A 2025 follow-up by some of the same authors shows, by emulation on measured channel data, that an attacker who knows the reference channel and the needle's effect on it could inject a signal that cancels the change caused by a needle insertion. It proposes a reconfigurable intelligent surface that randomizes the channel as a countermeasure.", "response": null, "sources": [ "S-1315", "S-0052", "S-3261" ] }, { "mech": "M-0013", "n": 1, "historical": false, "title": "Output nondeterminism leaves covert capacity", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Hashing cannot remove information hidden in the outputs themselves. The Secure Gateway Device paper estimates that about 0.1 bit per token remains even with seed-synchronized replay checks. For a 200k-GPU inference cluster at full load (2,000 tokens per GPU per second), that is about 40 Mbit/s of covert egress, enough to move a 1 TB model in under three days. The paper names this the core remaining challenge and points to deterministic replay or active scrubbing of hardware-induced entropy. An independent study found that an adversary who chooses the prompts roughly doubles the bits leaked per token under Gumbel-based inference verification; see Bounding unexplained information in outputs.", "response": null, "sources": [ "S-1300", "S-1507" ], "helps": [ { "by": "M-0002", "how": "Deterministic replay is one of the two remedies the flaw's source names." }, { "by": "M-0024", "how": "Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict." } ] }, { "mech": "M-0013", "n": 4, "historical": false, "title": "Residual side channels in simple passive setups", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Amodo's analysis of its own tapped prototype lists unvalidated header fields, timing of permitted traffic and variation in response formatting as residual channels, and concludes that the passive tap must be replaced by an active one.", "response": null, "sources": [ "S-1312" ] }, { "mech": "M-0001", "n": 1, "historical": false, "title": "Tolerance for numerical noise leaves a covert channel", "classification": "failure", "kind": "demonstrated-attack", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Schemes that accept approximate matches can put an upper bound on an adversary's covert bandwidth, but they cannot close the channel. The weight-exfiltration detector cut exfiltratable information to under 0.5%, not to zero, on a 30-billion-parameter mixture-of-experts model under benign prompt traffic. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token. Across six models, that cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target the check that outputs match the declared model.", "response": null, "sources": [ "S-0020", "S-0015", "S-1507" ], "helps": [ { "by": "M-0002", "how": "Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration." } ] }, { "mech": "M-0001", "n": 3, "historical": false, "title": "Some inference optimizations are not covered", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "TOPLOC's authors state that it cannot detect speculative decoding in which a cheaper model does the decoding. They did not test whether it distinguishes types of key-value (KV) cache compression. DiFR was evaluated only on sampling from a single model. Its authors sketch an extension to one speculative-decoding algorithm but do not test it.", "response": null, "sources": [ "S-1000", "S-0016" ] } ], "criticalMechanisms": [ "M-0012" ], "significantMechanisms": [ "M-0017", "M-0013", "M-0001" ], "familyContext": [], "scopeLimitations": [ { "mech": "M-0012", "n": 3, "historical": false, "title": "For private models, a user can confirm consistency but not content", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "When weights are not published, users can check that the same root hash is served each time, but not what the model is. Pairing the hash with an attested evaluation, as in Attestable Audits, is one proposed remedy.", "response": null, "sources": [ "S-0013", "S-0009" ] }, { "mech": "M-0017", "n": 2, "historical": false, "title": "Security depends on inspection protocols", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": "mechanism", "scope_note": "An inspection and protocol requirement drawn from safeguards and enclosure studies, not a reported break of a deployed AI verifier.", "related_finding": null, "description": "Johnston argues that a seal is no better than the protocols for using it, and that inspectors are usually given little useful information on how to detect tampering. The Sandia survey notes that larger enclosures are hard to inspect fully and that sensor data must be authenticated.", "response": null, "sources": [ "S-1318", "S-1316" ] }, { "mech": "M-0013", "n": 2, "historical": false, "title": "Some links cannot be passively tapped", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Cankaya notes that copper-connected scale-up domains (for example NVL72 racks and TPU v7 cubes) are much harder to tap than fibre, and that optical budgets make passive taps impractical on 400GBASE-SR8 multimode links. Amodo found no taps advertised for 53 GBaud links as of May 2026.", "response": null, "sources": [ "S-0031", "S-1310" ] }, { "mech": "M-0013", "n": 3, "historical": false, "title": "Encrypted fabrics hide plaintext from both parties", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Cankaya notes that with TEE-protected sessions whose keys are ephemeral and managed inside the TEE, neither the operator nor the manufacturer can recover session keys after the session, so tapped traffic could not be opened for recomputation. For other encrypted fabrics, the operator can retain keys.", "response": null, "sources": [ "S-0031" ] }, { "mech": "M-0013", "n": 5, "historical": false, "title": "Completeness rests on physical monitoring left out of scope", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "The Secure Gateway Device paper assumes the facility is physically monitored, and states that the whole architecture depends on the device being the only communication channel. It names radio emanation, power-line signalling and thermal channels as covert channels beyond that scope.", "response": null, "sources": [ "S-1300" ], "helps": [ { "by": "M-0022", "how": "Addresses the radio, power-line and thermal channels that network-level designs leave out." } ] }, { "mech": "M-0001", "n": 2, "historical": false, "title": "Only recorded traffic is checked", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Recomputation checks that recorded, declared workloads are correct. It cannot show that the record is complete. The published schemes do not cover hidden workloads run on the same compute, or substituted work. Rinberg et al. say their exfiltration-detection scheme cannot stand alone.", "response": null, "sources": [ "S-0017", "S-0015" ], "helps": [ { "by": "M-0013", "how": "Taps copy and hash all traffic on the monitored links, which bears on whether the traffic record is complete. They do not show what else ran on the same chips." } ] } ], "openQuestions": [], "minor": 1, "minorFindings": [ { "mech": "M-0001", "n": 4, "historical": false, "title": "Mixed hardware widens the honest baseline", "classification": "failure", "kind": "open-question", "severity": "minor", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "When honest reference runs span different GPU types, the spread of benign scores grows. In DiFR's tests on Qwen3-30B-A3B, pooling A100 and H200 runs left Token-DiFR unable to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy separated them. Matched provider and verifier environments, or pooling that weights rare large deviations, restored detection.", "response": null, "sources": [ "S-0016" ] } ], "minorBy": [ { "id": "M-0001", "n": 1 } ], "notDemonstrated": [ "M-0013" ], "newChip": [] }, "findings": [ { "mech": "M-0012", "record": "M-0012", "n": 1, "historical": false, "title": "Underlying attestation can be forged or relayed", "classification": "failure", "kind": "demonstrated-attack", "severity": "critical", "status": "open", "evidence_scope": "inherited", "scope_note": "Critical for weight binding against an operator with physical access to affected hardware, or with control of the hypervisor on an AMD SEV-SNP platform without AMD's fixes. PAL*M excludes physical attacks, and Tinfoil acknowledges this boundary.", "related_finding": { "record": "M-0008", "flaw": 1 }, "description": "The enclave route inherits the platform-specific TEE attestation failures. Intel TDX forgery and H100 relay were demonstrated with physical access and host control. Battering RAM defeated AMD SEV-SNP attestation on DDR4 servers; RMPocalypse did so from malicious host software on platforms without AMD's fixes. These demonstrate failures of the trust roots, not of each model-commitment protocol.", "response": "The TEE.fail authors report that physical interposer attacks are outside Intel's and AMD's threat models. AMD reports fixes for RMPocalypse.", "sources": [ "S-1202", "S-1210", "S-1212", "S-1213", "S-1206", "S-0012" ], "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-0012", "record": "M-0012", "n": 2, "historical": false, "title": "Launch-state attestation does not by itself cover weights loaded later", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "mitigated", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Attestation measures launch state, and weights are read from disk after boot. A signature checked at load time does not stop a malicious hypervisor from altering the disk afterwards. Tinfoil reports mitigating this with dm-verity checks on every read. Unmeasured runtime configuration remains a general risk.", "response": null, "sources": [ "S-0013", "S-0014" ] }, { "mech": "M-0012", "record": "M-0012", "n": 3, "historical": false, "title": "For private models, a user can confirm consistency but not content", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "When weights are not published, users can check that the same root hash is served each time, but not what the model is. Pairing the hash with an attested evaluation, as in Attestable Audits, is one proposed remedy.", "response": null, "sources": [ "S-0013", "S-0009" ] }, { "mech": "M-0017", "record": "M-0017", "n": 1, "historical": false, "title": "Seals are often defeated with simple methods", "classification": "failure", "kind": "demonstrated-attack", "severity": "significant", "status": "open", "evidence_scope": "mechanism", "scope_note": "Published defeats of general security seals. They warn about proposed verifier-device seals, but do not demonstrate defeat of an AI verification enclosure or sensor.", "related_finding": null, "description": "In 1996 a Los Alamos vulnerability assessment defeated all 94 security seals it examined, with 132 defeats in total, using rapid, inexpensive, low-tech methods. It found that seal cost did not predict security. In 2001 Johnston reported that high-tech seals are often easier to defeat than low-tech ones.", "response": null, "sources": [ "S-1317", "S-1318" ] }, { "mech": "M-0017", "record": "M-0017", "n": 2, "historical": false, "title": "Security depends on inspection protocols", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": "mechanism", "scope_note": "An inspection and protocol requirement drawn from safeguards and enclosure studies, not a reported break of a deployed AI verifier.", "related_finding": null, "description": "Johnston argues that a seal is no better than the protocols for using it, and that inspectors are usually given little useful information on how to detect tampering. The Sandia survey notes that larger enclosures are hard to inspect fully and that sensor data must be authenticated.", "response": null, "sources": [ "S-1318", "S-1316" ] }, { "mech": "M-0017", "record": "M-0017", "n": 3, "historical": false, "title": "Attack classes outside published models", "classification": "failure", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": "mechanism", "scope_note": "The radio compensation result is emulated using measured channel data under a known-reference attacker model. It is not a physical bypass demonstration against an AI verifier enclosure.", "related_finding": null, "description": "The authors of the batteryless cover say they cannot assess chemical-solvent attacks, which exceed their expertise, and deem cover removal impractical. Anti-Tamper Radio's reference can drift as the environment or measurement system ages; the authors suggest gradually renewing the reference. A 2025 follow-up by some of the same authors shows, by emulation on measured channel data, that an attacker who knows the reference channel and the needle's effect on it could inject a signal that cancels the change caused by a needle insertion. It proposes a reconfigurable intelligent surface that randomizes the channel as a countermeasure.", "response": null, "sources": [ "S-1315", "S-0052", "S-3261" ] }, { "mech": "M-0013", "record": "M-0013", "n": 1, "historical": false, "title": "Output nondeterminism leaves covert capacity", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Hashing cannot remove information hidden in the outputs themselves. The Secure Gateway Device paper estimates that about 0.1 bit per token remains even with seed-synchronized replay checks. For a 200k-GPU inference cluster at full load (2,000 tokens per GPU per second), that is about 40 Mbit/s of covert egress, enough to move a 1 TB model in under three days. The paper names this the core remaining challenge and points to deterministic replay or active scrubbing of hardware-induced entropy. An independent study found that an adversary who chooses the prompts roughly doubles the bits leaked per token under Gumbel-based inference verification; see Bounding unexplained information in outputs.", "response": null, "sources": [ "S-1300", "S-1507" ], "helps": [ { "by": "M-0002", "how": "Deterministic replay is one of the two remedies the flaw's source names." }, { "by": "M-0024", "how": "Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict." } ] }, { "mech": "M-0013", "record": "M-0013", "n": 2, "historical": false, "title": "Some links cannot be passively tapped", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Cankaya notes that copper-connected scale-up domains (for example NVL72 racks and TPU v7 cubes) are much harder to tap than fibre, and that optical budgets make passive taps impractical on 400GBASE-SR8 multimode links. Amodo found no taps advertised for 53 GBaud links as of May 2026.", "response": null, "sources": [ "S-0031", "S-1310" ] }, { "mech": "M-0013", "record": "M-0013", "n": 3, "historical": false, "title": "Encrypted fabrics hide plaintext from both parties", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Cankaya notes that with TEE-protected sessions whose keys are ephemeral and managed inside the TEE, neither the operator nor the manufacturer can recover session keys after the session, so tapped traffic could not be opened for recomputation. For other encrypted fabrics, the operator can retain keys.", "response": null, "sources": [ "S-0031" ] }, { "mech": "M-0013", "record": "M-0013", "n": 4, "historical": false, "title": "Residual side channels in simple passive setups", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Amodo's analysis of its own tapped prototype lists unvalidated header fields, timing of permitted traffic and variation in response formatting as residual channels, and concludes that the passive tap must be replaced by an active one.", "response": null, "sources": [ "S-1312" ] }, { "mech": "M-0013", "record": "M-0013", "n": 5, "historical": false, "title": "Completeness rests on physical monitoring left out of scope", "classification": "scope-limitation", "kind": "open-question", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "The Secure Gateway Device paper assumes the facility is physically monitored, and states that the whole architecture depends on the device being the only communication channel. It names radio emanation, power-line signalling and thermal channels as covert channels beyond that scope.", "response": null, "sources": [ "S-1300" ], "helps": [ { "by": "M-0022", "how": "Addresses the radio, power-line and thermal channels that network-level designs leave out." } ] }, { "mech": "M-0013", "record": "M-0013", "n": 6, "historical": false, "title": "Verifier dictionary attacks on hashes", "classification": "failure", "kind": "theoretical-argument", "severity": "minor", "status": "mitigated", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Hashes of very short outputs could be brute-forced by the verifier. The paper recommends hashing at least 5 tokens together, or at least 10 if the attacker filters for likely tokens.", "response": null, "sources": [ "S-1300" ] }, { "mech": "M-0001", "record": "M-0001", "n": 1, "historical": false, "title": "Tolerance for numerical noise leaves a covert channel", "classification": "failure", "kind": "demonstrated-attack", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Schemes that accept approximate matches can put an upper bound on an adversary's covert bandwidth, but they cannot close the channel. The weight-exfiltration detector cut exfiltratable information to under 0.5%, not to zero, on a 30-billion-parameter mixture-of-experts model under benign prompt traffic. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token. Across six models, that cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target the check that outputs match the declared model.", "response": null, "sources": [ "S-0020", "S-0015", "S-1507" ], "helps": [ { "by": "M-0002", "how": "Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration." } ] }, { "mech": "M-0001", "record": "M-0001", "n": 2, "historical": false, "title": "Only recorded traffic is checked", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Recomputation checks that recorded, declared workloads are correct. It cannot show that the record is complete. The published schemes do not cover hidden workloads run on the same compute, or substituted work. Rinberg et al. say their exfiltration-detection scheme cannot stand alone.", "response": null, "sources": [ "S-0017", "S-0015" ], "helps": [ { "by": "M-0013", "how": "Taps copy and hash all traffic on the monitored links, which bears on whether the traffic record is complete. They do not show what else ran on the same chips." } ] }, { "mech": "M-0001", "record": "M-0001", "n": 3, "historical": false, "title": "Some inference optimizations are not covered", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "TOPLOC's authors state that it cannot detect speculative decoding in which a cheaper model does the decoding. They did not test whether it distinguishes types of key-value (KV) cache compression. DiFR was evaluated only on sampling from a single model. Its authors sketch an extension to one speculative-decoding algorithm but do not test it.", "response": null, "sources": [ "S-1000", "S-0016" ] }, { "mech": "M-0001", "record": "M-0001", "n": 4, "historical": false, "title": "Mixed hardware widens the honest baseline", "classification": "failure", "kind": "open-question", "severity": "minor", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "When honest reference runs span different GPU types, the spread of benign scores grows. In DiFR's tests on Qwen3-30B-A3B, pooling A100 and H200 runs left Token-DiFR unable to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy separated them. Matched provider and verifier environments, or pooling that weights rare large deviations, restored detection.", "response": null, "sources": [ "S-0016" ] } ], "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-0012", "n": 1, "title": "Underlying attestation can be forged or relayed", "severity": "critical", "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-0002", "title": "Deterministic and bit-exact inference", "url": "https://trustbutveri.fyi/mechanisms/deterministic-inference/", "readiness": "R3", "development_status": { "code": "R3", "label": "Operational use", "short": "Operational use", "rank": 3, "legacy_code": "R3" }, "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": "flaw", "mech": "M-0013", "n": 1, "title": "Output nondeterminism leaves covert capacity", "severity": "significant", "how": "Deterministic replay is one of the two remedies the flaw's source names." }, { "kind": "flaw", "mech": "M-0001", "n": 1, "title": "Tolerance for numerical noise leaves a covert channel", "severity": "significant", "how": "Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration." }, { "kind": "blocker", "mech": "M-0013", "text": "Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove." } ] }, { "id": "M-0024", "title": "Bounding unexplained information in outputs", "url": "https://trustbutveri.fyi/mechanisms/bounding-unexplained-information/", "readiness": "R2", "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": [ { "n": 1, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1507", "S-0015" ] } ], "open_failures": { "critical": 0, "significant": 1, "minor": 0 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "flaw", "mech": "M-0013", "n": 1, "title": "Output nondeterminism leaves covert capacity", "severity": "significant", "how": "Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict." } ] }, { "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-0012", "text": "Attestation that resists physical attackers, for the enclave variant." } ] }, { "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-0013", "text": "Radio, power-line and thermal channels are not addressed by network-level designs." } ] } ], "goal": null, "design": null, "dependencies": { "prerequisites": [ { "id": "M-0008", "neededBy": [ "M-0012" ] }, { "id": "M-0002", "neededBy": [ "M-0013" ] }, { "id": "M-0022", "neededBy": [ "M-0013" ] } ], "shared": [], "blockers": [ { "mech": "M-0012", "n": 1, "historical": false, "text": "Attestation that resists physical attackers, for the enclave variant.", "theme": "hardware-trust", "blocked_by": "M-0008", "sources": [ "S-1202" ], "inProposal": false }, { "mech": "M-0017", "n": 1, "historical": false, "text": "No tamper-evident enclosure has been designed for AI verifier hardware at retrofit scale.", "theme": "hardware-trust", "blocked_by": null, "sources": [ "S-0018" ], "inProposal": null }, { "mech": "M-0017", "n": 2, "historical": false, "text": "Battery-backed designs add bulk, limit operating temperature (+10 °C to +35 °C for the IBM 4765) and complicate transport.", "theme": "performance-compatibility", "blocked_by": null, "sources": [ "S-1315" ], "inProposal": null }, { "mech": "M-0017", "n": 3, "historical": false, "text": "Active monitoring needs power, and visual inspection of large enclosures faces access limits.", "theme": "access-governance", "blocked_by": null, "sources": [ "S-1316" ], "inProposal": null }, { "mech": "M-0017", "n": 4, "historical": false, "text": "No evaluation has been published in the AI verification setting.", "theme": "adversarial-validation", "blocked_by": null, "sources": [ "S-0018" ], "inProposal": null }, { "mech": "M-0013", "n": 1, "historical": false, "text": "No complete verification tap has been demonstrated at production frontend link rates, and on the tested CPU no hash algorithm reached line rate with minimum-size frames.", "theme": "performance-compatibility", "blocked_by": null, "sources": [ "S-1311", "S-1310" ], "inProposal": null }, { "mech": "M-0013", "n": 2, "historical": false, "text": "Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove.", "theme": "evidence-binding", "blocked_by": "M-0002", "sources": [ "S-1300" ], "inProposal": false }, { "mech": "M-0013", "n": 3, "historical": false, "text": "Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them.", "theme": "hardware-trust", "blocked_by": "M-0017", "sources": [ "S-1300", "S-0018" ], "inProposal": true }, { "mech": "M-0013", "n": 4, "historical": false, "text": "Radio, power-line and thermal channels are not addressed by network-level designs.", "theme": "coverage-hidden-compute", "blocked_by": "M-0022", "sources": [ "S-1300" ], "inProposal": false }, { "mech": "M-0013", "n": 5, "historical": false, "text": "Red-teaming by specialists is called for but has not been reported.", "theme": "adversarial-validation", "blocked_by": null, "sources": [ "S-1300" ], "inProposal": null }, { "mech": "M-0001", "n": 1, "historical": false, "text": "In tap-based retrofit designs, recording all inference traffic needs network taps and recomputation servers that can ingest it, in the worst case one recomputation-server network interface per inference front-end interface.", "theme": "coverage-hidden-compute", "blocked_by": "M-0013", "sources": [ "S-1008", "S-0067" ], "inProposal": true }, { "mech": "M-0001", "n": 2, "historical": false, "text": "In retrofit designs, the recomputation server must sit inside the prover's data centre, possibly under the prover's physical control, and still be protected from a compromised provider, which Amodo rates 'not on track'.", "theme": "hardware-trust", "blocked_by": null, "sources": [ "S-1008", "S-0015" ], "inProposal": null }, { "mech": "M-0001", "n": 3, "historical": false, "text": "No independent red-team of a recomputation consistency check has been published (the one independent attack study targets the weight-exfiltration bound), and Amodo rates recomputation red-teaming 'not started'.", "theme": "adversarial-validation", "blocked_by": null, "sources": [ "S-1008", "S-1507" ], "inProposal": null }, { "mech": "M-0001", "n": 4, "historical": false, "text": "Tolerance-based checks need calibration on trusted hardware and exact knowledge of the provider's sampling procedure, and in one prototype a sampling-implementation mismatch produced large spurious differences.", "theme": "performance-compatibility", "blocked_by": null, "sources": [ "S-0016", "S-1006" ], "inProposal": null }, { "mech": "M-0001", "n": 5, "historical": false, "text": "The verifier needs the model weights, so checking a closed-weights model requires a trusted, confidential recomputation environment, which the retrofit designs place inside the prover's facility.", "theme": "privacy-leakage", "blocked_by": null, "sources": [ "S-0016", "S-0017", "S-0018" ], "inProposal": null } ] }, "exposure": { "weights": { "shown": [], "partial": [ "M-0013", "M-0001" ], "hidden": [ "M-0012" ], "none": [ "M-0017" ], "unknown": [] }, "io": { "shown": [], "partial": [ "M-0013", "M-0001" ], "hidden": [], "none": [ "M-0017" ], "unknown": [ "M-0012" ] }, "training": { "shown": [], "partial": [ "M-0013" ], "hidden": [], "none": [ "M-0012", "M-0017", "M-0001" ], "unknown": [] } }, "implementations": [ { "mechanism": "M-0012", "selected": null, "implementations": [ { "id": "I-0007", "title": "Attestable Audits", "url": "https://trustbutveri.fyi/implementations/attestable-audits/" }, { "id": "I-0022", "title": "PAL*M", "url": "https://trustbutveri.fyi/implementations/palm/" }, { "id": "I-0006", "title": "Tinfoil model identity (Modelwrap)", "url": "https://trustbutveri.fyi/implementations/tinfoil-model-identity/" } ] }, { "mechanism": "M-0017", "selected": null, "implementations": [ { "id": "I-0011", "title": "AI 2040 inference-only verification stack", "url": "https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/" } ] }, { "mechanism": "M-0013", "selected": null, "implementations": [ { "id": "I-0011", "title": "AI 2040 inference-only verification stack", "url": "https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/" }, { "id": "I-0012", "title": "Low-trust AI compute verification system overview", "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/" }, { "id": "I-0008", "title": "SASH confidential network logger", "url": "https://trustbutveri.fyi/implementations/sash-confidential-network-logger/" } ] }, { "mechanism": "M-0001", "selected": null, "implementations": [ { "id": "I-0011", "title": "AI 2040 inference-only verification stack", "url": "https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/" }, { "id": "I-0002", "title": "DiFR (Divergence From Reference)", "url": "https://trustbutveri.fyi/implementations/difr/" }, { "id": "I-0012", "title": "Low-trust AI compute verification system overview", "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/" }, { "id": "I-0008", "title": "SASH confidential network logger", "url": "https://trustbutveri.fyi/implementations/sash-confidential-network-logger/" }, { "id": "I-0001", "title": "TOPLOC", "url": "https://trustbutveri.fyi/implementations/toploc/" } ] } ], "sources": [ { "id": "S-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/" }, { "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-1206", "title": "A primer on secure enclaves", "authors": "Tinfoil", "year": 2026, "url": "https://docs.tinfoil.sh/verification/secure-enclave-primer", "path": "/sources/tinfoil-docs-secure-enclave-primer/" }, { "id": "S-1207", "title": "Backend infrastructure", "authors": "Tinfoil", "year": 2026, "url": "https://docs.tinfoil.sh/verification/attestation-architecture", "path": "/sources/tinfoil-docs-attestation-architecture/" }, { "id": "S-1208", "title": "How verification works in Tinfoil", "authors": "Tinfoil", "year": 2026, "url": "https://docs.tinfoil.sh/verification/verification-in-tinfoil", "path": "/sources/tinfoil-docs-verification-in-tinfoil/" }, { "id": "S-1209", "title": "modelwrap: Reproducible dm-verity read-only image of Huggingface models", "authors": "Tinfoil", "year": 2026, "url": "https://github.com/tinfoilsh/modelwrap", "path": "/sources/tinfoil-modelwrap-code/" }, { "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-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-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-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-0052", "title": "Anti-Tamper Radio: System-Level Tamper Detection for Computing Systems", "authors": "P. Staat et al.", "year": 2022, "url": "https://ieeexplore.ieee.org/document/9833631/", "path": "/sources/staat-anti-tamper-radio/" }, { "id": "S-1315", "title": "Secure Physical Enclosures from Covers with Tamper-Resistance", "authors": "V. Immler et al.", "year": 2019, "url": "https://tches.iacr.org/index.php/TCHES/article/view/7334", "path": "/sources/immler-secure-physical-enclosures-covers/" }, { "id": "S-0051", "title": "ImpedanceVerif: On-Chip Impedance Sensing for System-Level Tampering Detection", "authors": "T. Mosavirik et al.", "year": 2023, "url": "https://eprint.iacr.org/2022/946", "path": "/sources/mosavirik-impedanceverif/" }, { "id": "S-0050", "title": "IBM 4765 Cryptographic Coprocessor Security Module: Security Policy", "authors": "IBM Corporation", "year": 2012, "url": "https://csrc.nist.gov/csrc/media/projects/cryptographic-module-validation-program/documents/security-policies/140sp1505.pdf", "path": "/sources/ibm-4765-security-policy/" }, { "id": "S-3262", "title": "PHYSEC SEAL: Change detection for maximum safety", "authors": "PHYSEC GmbH", "year": 2026, "url": "https://www.physec.de/en/solutions/physec-seal/", "path": "/sources/physec-seal/" }, { "id": "S-1316", "title": "Tamper-Indicating Enclosures, A Current Survey", "authors": "H. A. Smartt & Z. N. Gastelum", "year": 2015, "url": "https://www.osti.gov/servlets/purl/1256541", "path": "/sources/smartt-tamper-indicating-enclosures-survey/" }, { "id": "S-0018", "title": "A System Overview for Near-Term, Low-Trust AI Compute Verification", "authors": "N. Cankaya", "year": 2026, "url": "https://intelligence.org/wp-content/uploads/2026/06/A-system-overview-for-near-term-low-trust-AI-compute-verification.pdf", "path": "/sources/cankaya-system-overview-low-trust-compute-verification/" }, { "id": "S-1317", "title": "Physical Security and Tamper-Indicating Devices", "authors": "R. G. Johnston & A. R. E. Garcia", "year": 1996, "url": "https://www.osti.gov/servlets/purl/459707", "path": "/sources/johnston-physical-security-tamper-indicating-devices/" }, { "id": "S-1318", "title": "Tamper Detection for Safeguards and Treaty Monitoring: Fantasies, Realities, and Potentials", "authors": "R. G. Johnston", "year": 2001, "url": "https://www.nonproliferation.org/wp-content/uploads/npr/81john.pdf", "path": "/sources/johnston-tamper-detection-safeguards-treaty-monitoring/" }, { "id": "S-3261", "title": "Anti-Tamper Radio Meets Reconfigurable Intelligent Surface for System-Level Tamper Detection", "authors": "M. S. Tabar et al.", "year": 2025, "url": "https://arxiv.org/abs/2503.14279", "path": "/sources/tabar-anti-tamper-radio-ris/" }, { "id": "S-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-0031", "title": "The Fundamentals and Feasibility of Secure Network Taps for Verifying AI Datacenter Use", "authors": "N. Cankaya", "year": 2026, "url": "https://nacicankaya.substack.com/p/research-note-the-fundamentals-and", "path": "/sources/cankaya-secure-network-taps/" }, { "id": "S-0067", "title": "Verification Plan", "authors": "R. Dean", "year": 2026, "url": "https://ai-2040.com/supplements/verification-plan", "path": "/sources/dean-verification-plan/" }, { "id": "S-1312", "title": "Fitting a Network TAP to our Inference Verification Prototype", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/notes/2026-09-15-network-tap-inference-verification/", "path": "/sources/amodo-network-tap-inference-verification-prototype/" }, { "id": "S-1007", "title": "Amodo-Design/Inference-Recomputation-Prototype (GitHub repository)", "authors": "Amodo Design", "year": 2026, "url": "https://github.com/Amodo-Design/Inference-Recomputation-Prototype", "path": "/sources/amodo-inference-recomputation-prototype-code/" }, { "id": "S-1319", "title": "inference-verification: Inference Verification Prototype", "authors": "Singapore AI Safety Hub (SASH)", "year": 2026, "url": "https://github.com/sg-ai-safety-hub/inference-verification", "path": "/sources/sash-inference-verification-repo/" }, { "id": "S-1320", "title": "Internationalising AI Verification", "authors": "Singapore AI Safety Hub (SASH)", "year": 2026, "url": "https://www.aisafety.sg/research/internationalising-ai-verification", "path": "/sources/sash-internationalising-ai-verification/" }, { "id": "S-1507", "title": "Adversarial Entropy Inflation Against Gumbel-Based Inference Verification", "authors": "N. Kezins", "year": 2026, "url": "https://arxiv.org/abs/2608.23375", "path": "/sources/kezins-adversarial-entropy-inflation/" }, { "id": "S-1310", "title": "Network Tapping for AI Verification: A Technical Assessment", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/notes/2026-05-03-network-tapping/", "path": "/sources/amodo-network-tapping-technical-assessment/" }, { "id": "S-0015", "title": "Verifying LLM Inference to Detect Model Weight Exfiltration", "authors": "R. Rinberg et al.", "year": 2025, "url": "https://arxiv.org/abs/2511.02620", "path": "/sources/rinberg-verifying-llm-inference-weight-exfiltration/" }, { "id": "S-0016", "title": "DiFR: Inference Verification Despite Nondeterminism", "authors": "A. Karvonen et al.", "year": 2025, "url": "https://arxiv.org/abs/2511.20621", "path": "/sources/karvonen-difr/" }, { "id": "S-1000", "title": "TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference", "authors": "J. M. Ong et al.", "year": 2025, "url": "https://proceedings.mlr.press/v267/ong25a.html", "path": "/sources/ong-toploc/" }, { "id": "S-1001", "title": "PrimeIntellect-ai/toploc (GitHub repository)", "authors": "Prime Intellect", "year": 2025, "url": "https://github.com/PrimeIntellect-ai/toploc", "path": "/sources/primeintellect-toploc-code/" }, { "id": "S-1003", "title": "INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning", "authors": "Prime Intellect Team et al.", "year": 2025, "url": "https://arxiv.org/abs/2505.07291", "path": "/sources/primeintellect-intellect-2/" }, { "id": "S-1005", "title": "adamkarvonen/difr (GitHub repository)", "authors": "A. Karvonen", "year": 2025, "url": "https://github.com/adamkarvonen/difr", "path": "/sources/karvonen-difr-code/" }, { "id": "S-1006", "title": "Scaling Recomputation Inference Verification", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/notes/2026-09-02-scaling-recomputation-inference-verification/", "path": "/sources/amodo-scaling-recomputation-inference-verification/" }, { "id": "S-1008", "title": "AI 2040 Plan A — Verification SITREP", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/ai-verification/plan-a-sitrep/", "path": "/sources/amodo-plan-a-verification-sitrep/" }, { "id": "S-3000", "title": "SYNTHETIC-2 Release: Four Million Collaboratively Generated Reasoning Traces", "authors": "Prime Intellect", "year": 2025, "url": "https://www.primeintellect.ai/blog/synthetic-2-release", "path": "/sources/primeintellect-synthetic-2-release/" }, { "id": "S-3001", "title": "An Inference Verification Prototype — Stage 1", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/notes/2026-06-29-inference-verification-prototype/", "path": "/sources/amodo-inference-verification-prototype-stage-1/" }, { "id": "S-0020", "title": "Bit-Exact AI Inference Verification Without Performance Tradeoffs", "authors": "N. Cankaya", "year": 2026, "url": "https://arxiv.org/abs/2606.00279", "path": "/sources/cankaya-bit-exact-inference-verification/" }, { "id": "S-0017", "title": "Example Schemes for Verifying High-Stakes AI Agreements", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/notes/2026-06-23-verification-algorithms/", "path": "/sources/amodo-example-schemes-high-stakes-ai-agreements/" }, { "id": "S-1311", "title": "Network Traffic Hashing", "authors": "Amodo Design", "year": 2026, "url": "https://amododesign.com/notes/2026-07-03-network-traffic-hashing/", "path": "/sources/amodo-network-traffic-hashing/" } ] }