{ "schema_version": "1.2", "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0023,M-0018&cols=sees", "data_generated": "2026-10-08", "definitions": { "methodology": "https://trustbutveri.fyi/about/methodology/", "readiness": "https://trustbutveri.fyi/about/readiness/", "filters": [ { "id": "prover", "label": "Prover", "question": "How far can the party being checked be trusted?", "options": [ { "value": "cooperative", "label": "Cooperative" }, { "value": "semi-trusted", "label": "Semi-trusted" }, { "value": "adversarial", "label": "Adversarial" } ], "rule": "Keeps mechanisms whose threat model holds against at least this prover. Adversarial is the strongest assumption.", "about": "The prover is the party being checked. Semi-trusted designs rely on part of its stack: usually the chip vendor's hardware root of trust, its firmware or counters, or its supply-chain records. Adversarial designs aim to hold even if it cheats wherever the checks allow, within their stated assumptions." }, { "id": "onsite", "label": "Verifier devices on site", "question": "May the verifier install its own hardware at the prover's sites?", "options": [ { "value": "no", "label": "Not allowed" } ], "rule": "\"Not allowed\" removes mechanisms that need a retrofit device, such as a network tap or a sealed sensor.", "about": "Some mechanisms need a device the verifier owns or trusts at the prover's facility, such as a network tap, a bandwidth limiter or a sealed sensor. Choose Not allowed when the setting rules that out. Inspectors are not covered." }, { "id": "coop", "label": "Prover cooperation", "question": "How much must the prover take part?", "options": [ { "value": "partial", "label": "Partial at most" }, { "value": "none", "label": "Not required" } ], "rule": "\"Partial at most\" removes mechanisms that need the prover's active participation. \"Not required\" keeps only those that work without it.", "about": "Required: the prover takes part, for example by logging requests, producing proofs or opening records. Partial: some access, such as installing a device. Not required: works from outside, such as satellite imagery." }, { "id": "chips", "label": "Chips", "question": "May the proposal depend on new chip designs?", "options": [ { "value": "existing", "label": "Existing chips only" } ], "rule": "\"Existing chips only\" removes mechanisms that need changes to future chip designs.", "about": "New chip features take years to reach a deployed fleet and cover only chips made after they ship. Mechanisms that use shipping features, such as trusted execution environments or performance counters, stay." }, { "id": "ready", "label": "Minimum readiness", "question": "How mature must each mechanism be?", "options": [ { "value": "R1", "label": "R1 Proposed" }, { "value": "R2", "label": "R2 Demonstrated" }, { "value": "R3", "label": "R3 In production" }, { "value": "R4", "label": "R4 Deployment-ready" } ], "rule": "Keeps mechanisms whose readiness level is at least this one.", "about": "A level describes the public evidence for a mechanism's stated use, not its cost or feasibility. R3 can still have open critical flaws." }, { "id": "tested", "label": "Attack testing", "question": "How hard has each mechanism been attacked in public?", "options": [ { "value": "analysis", "label": "Published analysis" }, { "value": "red-teamed", "label": "Red-teamed" }, { "value": "independent-red-team", "label": "Independent red-team" } ], "rule": "Keeps mechanisms whose strongest published attack testing is at least this.", "about": "The strongest published attempt to break the mechanism for its verification use: a security analysis, red-teaming by its developers or collaborators, or a red team independent of them." }, { "id": "hide", "label": "Keep hidden from the verifier", "question": "What must the verifier never see?", "options": [ { "value": "weights", "label": "Model weights" }, { "value": "io", "label": "Inputs and outputs" }, { "value": "training", "label": "Training data" } ], "rule": "Removes mechanisms that show the asset to the verifier. Conditional or unspecified exposure stays with a note and needs checking against the privacy requirement.", "about": "Model weights: the checked model's parameters. Inputs and outputs: the requests a deployed model serves and its responses. Training data: what a model was trained on. Each mechanism's exposure is the editors' reading of its record: shown, depends on the design (kept, with a note), hidden, not involved, or unspecified for a selected implementation. Code and configuration are not covered yet." } ], "exposure": "For model weights, inputs and outputs, and training data. This is the editors' reading of each mechanism's record (its threat model, how it works and its limitations), not a field of the record. Shown: the verifier sees it. Depends: on the design or variant, or the verifier sees only samples. Hidden: the verifier sees only commitments, hashes, proofs or results. Not involved: the record does not handle it. Unspecified: the selected implementation has no asset-specific assessment here.", "claim_status": { "addressed": "A mechanism in the proposal is aimed at this claim and is not excluded by the filters.", "partly-addressed": "Only supporting mechanisms, or mechanisms aimed at it that the filters exclude.", "unaddressed": "No mechanism in the proposal addresses this claim." }, "finding_scope": "Evidence scope describes where a finding was demonstrated; it does not establish applicability to every implementation in the mechanism family.", "claim_finding_scope": "open_critical_findings names active findings on the assessed records; open_critical_context names conditional family findings whose implementation applicability is unassessed.", "legacy_status": "The status field retains covered/partial/none for compatibility. It names claim links, never successful verification. Use claim_status and status_label for presentation." }, "filters": { "prover": "", "onsite": "", "coop": "", "chips": "", "ready": "", "tested": "", "hide": [] }, "mechanisms_passing_filters": 25, "claims": [], "mechanisms": [ { "id": "M-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/" }, "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" ] }, "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-0018", "title": "Chip location verification", "url": "https://trustbutveri.fyi/mechanisms/chip-location-verification/", "assessment_record": { "id": "M-0018", "title": "Chip location verification", "url": "https://trustbutveri.fyi/mechanisms/chip-location-verification/" }, "selected_implementation": null, "readiness": { "level": "R1", "scope": "bounding how far a chip is from trusted landmark servers when checked", "confidence": "medium", "evidence": [ "S-1400", "S-1401", "S-3570", "S-1402", "S-1404", "S-1403", "S-0056" ] }, "assessed_properties": { "threat_model": "adversarial", "hardware_requirement": "existing-features", "prover_cooperation": "required", "adversarial_evaluation": "analysis" }, "claims": [], "exposure": { "weights": "none", "io": "none", "training": "none", "note": "Times signed replies from chips; it does not handle model data." }, "family_finding_context": [], "filter_issues": [] } ], "strengths": { "covered": [], "production": [], "adversarial": [ "M-0018" ], "noNewHardware": [ "M-0023", "M-0018" ], "mitigated": [], "notCounted": [] }, "properties": { "covered": [], "production": [], "adversarial": [ "M-0018" ], "noNewHardware": [ "M-0023", "M-0018" ], "mitigated": [], "notCounted": [] }, "attack_testing": [ { "id": "M-0023", "record": "M-0023", "evaluation": "analysis", "in_setting": true }, { "id": "M-0018", "record": "M-0018", "evaluation": "analysis", "in_setting": true } ], "selected_implementations": {}, "weaknesses": { "gaps": [], "excluded": [], "unlinked": [], "critical": [], "significant": [ { "mech": "M-0023", "n": 1, "title": "Attestation shows a safeguard ran, not that it is effective", "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, "title": "Selective attestation leaves traffic uncovered", "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, "title": "Measurements may omit behaviour-relevant configuration or runtime changes", "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", "n": 4, "title": "Components outside the attested boundary", "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, "title": "Memory-bus interposition extracts attestation keys and forges attestations", "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-0018", "n": 1, "title": "Extracting a chip's key lets another device answer for it", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Ping-based protocols rely on cryptographic keys stored on the chip. Tee and Happel argue that an adversary with physical access could extract these keys and so compromise location verification. They propose GPU fingerprints as a mitigation, so far tested on 24 GPUs. Brass and Aarne assume the keys are stored securely, for example in a TPM.", "response": null, "sources": [ "S-1403", "S-1400" ] }, { "mech": "M-0018", "n": 2, "title": "Added delay can shift an estimated position", "kind": "demonstrated-attack", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Brass and Aarne cite internet-geolocation research in which artificially increased round-trip times moved the estimated location by up to 1,000 km, with a 74% chance of avoiding detection. Avellar and Grunewald list inflated ping times from circuitous routing as an evasion route. Added delay only loosens a distance bound, and Brass and Aarne propose a hard time limit as the counter: a chip that replies too slowly cannot be ruled out of a restricted location.", "response": null, "sources": [ "S-1400", "S-1402" ] }, { "mech": "M-0018", "n": 3, "title": "Faster-than-assumed network paths", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Brass and Aarne list dark fibre and other private high-speed interconnects as ways to lower measured delays artificially. They judge that leasing dark fibre would probably not be a considerable challenge for covertly or openly adversarial actors. Avellar and Grunewald note that this can make a chip appear to be somewhere else entirely. A limit set at the vacuum speed of light cannot be beaten, but it makes honest chips fail more often.", "response": null, "sources": [ "S-1400", "S-1402" ] }, { "mech": "M-0018", "n": 4, "title": "Compromised landmarks can falsify measurements", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "A party that controls landmark servers can report false timing. Brass and Aarne cite research in which manipulating a third of the landmarks shifted the estimated location by about 700 km. Avellar and Grunewald note that compromised landmarks let adversaries spoof travel-time measurements directly. The draft specification asks verifiers to require anchors in diverse places, run by several independent operators.", "response": null, "sources": [ "S-1400", "S-1402", "S-1404" ] } ], "criticalMechanisms": [], "significantMechanisms": [ "M-0023", "M-0018" ], "familyContext": [], "minor": 0, "minorFindings": [], "minorBy": [], "notDemonstrated": [ "M-0018" ], "newChip": [] }, "findings": [ { "mech": "M-0023", "record": "M-0023", "n": 1, "title": "Attestation shows a safeguard ran, not that it is effective", "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, "title": "Selective attestation leaves traffic uncovered", "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, "title": "Measurements may omit behaviour-relevant configuration or runtime changes", "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, "title": "Components outside the attested boundary", "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, "title": "Memory-bus interposition extracts attestation keys and forges attestations", "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-0018", "record": "M-0018", "n": 1, "title": "Extracting a chip's key lets another device answer for it", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Ping-based protocols rely on cryptographic keys stored on the chip. Tee and Happel argue that an adversary with physical access could extract these keys and so compromise location verification. They propose GPU fingerprints as a mitigation, so far tested on 24 GPUs. Brass and Aarne assume the keys are stored securely, for example in a TPM.", "response": null, "sources": [ "S-1403", "S-1400" ] }, { "mech": "M-0018", "record": "M-0018", "n": 2, "title": "Added delay can shift an estimated position", "kind": "demonstrated-attack", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Brass and Aarne cite internet-geolocation research in which artificially increased round-trip times moved the estimated location by up to 1,000 km, with a 74% chance of avoiding detection. Avellar and Grunewald list inflated ping times from circuitous routing as an evasion route. Added delay only loosens a distance bound, and Brass and Aarne propose a hard time limit as the counter: a chip that replies too slowly cannot be ruled out of a restricted location.", "response": null, "sources": [ "S-1400", "S-1402" ] }, { "mech": "M-0018", "record": "M-0018", "n": 3, "title": "Faster-than-assumed network paths", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Brass and Aarne list dark fibre and other private high-speed interconnects as ways to lower measured delays artificially. They judge that leasing dark fibre would probably not be a considerable challenge for covertly or openly adversarial actors. Avellar and Grunewald note that this can make a chip appear to be somewhere else entirely. A limit set at the vacuum speed of light cannot be beaten, but it makes honest chips fail more often.", "response": null, "sources": [ "S-1400", "S-1402" ] }, { "mech": "M-0018", "record": "M-0018", "n": 4, "title": "Compromised landmarks can falsify measurements", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "A party that controls landmark servers can report false timing. Brass and Aarne cite research in which manipulating a third of the landmarks shifted the estimated location by about 700 km. Avellar and Grunewald note that compromised landmarks let adversaries spoof travel-time measurements directly. The draft specification asks verifiers to require anchors in diverse places, run by several independent operators.", "response": null, "sources": [ "S-1400", "S-1402", "S-1404" ] } ], "possible_additions": [ { "id": "M-0010", "title": "On-chip telemetry from timing, memory and performance counters", "url": "https://trustbutveri.fyi/mechanisms/on-chip-telemetry/", "readiness": "R2", "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "flaw", "mech": "M-0023", "n": 2, "title": "Selective attestation leaves traffic uncovered", "severity": "significant", "how": "On-chip counters are a proposed route to evidence about everything a chip runs, including a second virtual machine that skips the safeguard." } ] }, { "id": "M-0009", "title": "Hardware-enabled guarantees (flexHEG) and guarantee processors", "url": "https://trustbutveri.fyi/mechanisms/flexheg-guarantee-processors/", "readiness": "R1", "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": "Model identity attestation", "url": "https://trustbutveri.fyi/mechanisms/model-identity-attestation/", "readiness": "R3", "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", "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." }, { "kind": "prerequisite", "mech": "M-0018" } ] } ], "goal": null, "design": null, "dependencies": { "prerequisites": [ { "id": "M-0008", "neededBy": [ "M-0023", "M-0018" ] }, { "id": "M-0012", "neededBy": [ "M-0023" ] } ], "shared": [ { "id": "M-0008", "by": [ "M-0023", "M-0018" ], "inProposal": false } ], "blockers": [ { "mech": "M-0023", "n": 1, "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, "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, "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, "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, "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-0018", "n": 1, "text": "No public code or reproducible end-to-end location results are available for the reported H100 prototype.", "theme": "adversarial-validation", "blocked_by": null, "sources": [ "S-1401", "S-3570" ], "inProposal": null }, { "mech": "M-0018", "n": 2, "text": "Per-chip keys must be provisioned and protected against extraction; hardware-integrated, tamper-resistant versions still need R&D.", "theme": "hardware-trust", "blocked_by": null, "sources": [ "S-1400", "S-1403", "S-0007" ], "inProposal": null }, { "mech": "M-0018", "n": 3, "text": "The time limit forces a trade-off: a limit at the speed of light in fibre can be beaten by faster links, while one at the vacuum speed of light makes honest chips fail often.", "theme": "protocol-soundness", "blocked_by": null, "sources": [ "S-1400" ], "inProposal": null }, { "mech": "M-0018", "n": 4, "text": "A trusted landmark network must be built and secured, and who should operate it, under what oversight, is unsettled.", "theme": "access-governance", "blocked_by": null, "sources": [ "S-1400", "S-1402" ], "inProposal": null } ] }, "exposure": { "weights": { "shown": [], "partial": [ "M-0023" ], "hidden": [], "none": [ "M-0018" ], "unknown": [] }, "io": { "shown": [], "partial": [ "M-0023" ], "hidden": [], "none": [ "M-0018" ], "unknown": [] }, "training": { "shown": [], "partial": [], "hidden": [], "none": [ "M-0023", "M-0018" ], "unknown": [] } }, "implementations": [ { "mechanism": "M-0023", "selected": null, "implementations": [] }, { "mechanism": "M-0018", "selected": null, "implementations": [ { "id": "I-0009", "title": "Lucid sovereignty (location) certificates", "url": "https://trustbutveri.fyi/implementations/lucid-location-certificates/" } ] } ], "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-1400", "title": "Location Verification for AI Chips", "authors": "A. Brass & O. Aarne", "year": 2024, "url": "https://www.iaps.ai/research/location-verification-for-ai-chips", "path": "/sources/brass-location-verification-ai-chips/" }, { "id": "S-1401", "title": "Location Verification for AI Chips (issue brief)", "authors": "A. Brass", "year": 2025, "url": "https://static1.squarespace.com/static/64edf8e7f2b10d716b5ba0e1/t/6827b67275666f3757f134ea/1747433075281/Location+Verification+two-pager.pdf", "path": "/sources/brass-location-verification-issue-brief/" }, { "id": "S-3570", "title": "Ping-based Location", "authors": "Ulyssean", "year": 2025, "url": "https://ping-location.info/", "path": "/sources/ulyssean-ping-based-location-demo/" }, { "id": "S-1402", "title": "Near-Term Verification Methods for AI Chip Exports", "authors": "B. Avellar & E. Grunewald", "year": 2026, "url": "https://www.iaps.ai/research/near-term-verification-methods-for-ai-chip-exports", "path": "/sources/avellar-near-term-verification-ai-chip-exports/" }, { "id": "S-1404", "title": "Sovereignty Certificates: draft specification, version 0.1.0", "authors": "Sovereignty Certificates Working Group", "year": 2025, "url": "https://github.com/Lucid-Computing/sovereignty-certificate-specification", "path": "/sources/sovereignty-certificates-specification/" }, { "id": "S-1403", "title": "GPU Fingerprinting for Location Verification", "authors": "W. Tee & J. Happel", "year": 2026, "url": "https://arxiv.org/abs/2605.01930", "path": "/sources/tee-gpu-fingerprinting-location-verification/" }, { "id": "S-0056", "title": "Secure, Governable Chips: Using On-Chip Mechanisms to Manage National Security Risks from AI & Advanced Computing", "authors": "O. Aarne et al.", "year": 2024, "url": "https://www.cnas.org/publications/reports/secure-governable-chips", "path": "/sources/aarne-secure-governable-chips/" }, { "id": "S-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/" }, { "id": "S-0007", "title": "Hardware-Level Governance of AI Compute: A Feasibility Taxonomy for Regulatory Compliance and Treaty Verification", "authors": "S. Ansari", "year": 2026, "url": "https://arxiv.org/abs/2604.04712", "path": "/sources/ansari-hardware-level-governance-ai-compute/" } ] }