{ "schema_version": "1.3", "url": "https://trustbutveri.fyi/explorer/?mechanisms=M-0023,M-0001,M-0013&ready=R1", "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": "R1", "tested": "", "hide": [] }, "mechanisms_passing_filters": 25, "claims": [], "mechanisms": [ { "id": "M-0023", "title": "Safeguard attestation", "url": "https://trustbutveri.fyi/mechanisms/safeguard-attestation/", "assessment_record": { "id": "M-0023", "title": "Safeguard attestation", "url": "https://trustbutveri.fyi/mechanisms/safeguard-attestation/" }, "finding_counts": { "failure": 2, "scope_limitation": 3, "open_question": 0, "open_failures": { "critical": 0, "significant": 2, "minor": 0 } }, "selected_implementation": null, "readiness": { "level": "R2", "scope": "attesting that a declared safeguard mediated a service's responses", "confidence": "low", "evidence": [ "S-1500", "S-1501", "S-3362", "S-0012", "S-1503", "S-1504", "S-1202", "S-3126" ] }, "development_status": { "code": "R2", "label": "Research demonstration", "short": "Research demo", "rank": 2, "legacy_code": "R2" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 4, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1500", "S-1501" ] }, { "n": 5, "severity": "significant", "status": "open", "evidence_scope": "inherited", "sources": [ "S-1202", "S-3126", "S-1210", "S-1212", "S-1213", "S-0012", "S-0014", "S-1500", "S-0018" ], "related_finding": { "record": "M-0008", "flaw": 1 } } ], "open_failures": { "critical": 0, "significant": 2, "minor": 0 } }, "assessed_properties": { "threat_model": "semi-trusted", "hardware_requirement": "existing-features", "prover_cooperation": "required", "adversarial_evaluation": "analysis" }, "claims": [], "exposure": { "weights": "partial", "io": "partial", "training": "none", "note": "The enclave route signs hashes of the safeguard, request and response; a low-trust design has the verifier re-run and screen sampled requests itself." }, "family_finding_context": [], "filter_issues": [] }, { "id": "M-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": [] }, { "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": [] } ], "strengths": { "covered": [], "production": [ "M-0001" ], "operationalUse": [ "M-0001" ], "adversarial": [ "M-0001", "M-0013" ], "noNewHardware": [ "M-0023", "M-0001" ], "mitigated": [ { "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-0001" ], "operationalUse": [ "M-0001" ], "adversarial": [ "M-0001", "M-0013" ], "noNewHardware": [ "M-0023", "M-0001" ], "mitigated": [ { "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-0023", "record": "M-0023", "evaluation": "analysis", "in_setting": true }, { "id": "M-0001", "record": "M-0001", "evaluation": "analysis", "in_setting": true }, { "id": "M-0013", "record": "M-0013", "evaluation": "analysis", "in_setting": true } ], "selected_implementations": {}, "weaknesses": { "gaps": [], "excluded": [], "unlinked": [], "critical": [], "significant": [ { "mech": "M-0023", "n": 4, "historical": false, "title": "Components outside the attested boundary", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "In the proof-of-guardrail experiments, the guardrail model and the agent's backend model were both reached through external APIs, and the authors leave the decision to trust those APIs to the verifier. The measured wrapper must also have no vulnerability that lets the unmeasured agent bypass the guardrail, for example by executing arbitrary commands inside the enclave. The code's README states that the enclave does not currently restrict the agent's arbitrary command execution, which could be used to bypass guardrails.", "response": null, "sources": [ "S-1500", "S-1501" ] }, { "mech": "M-0023", "n": 5, "historical": false, "title": "Memory-bus interposition extracts attestation keys and forges attestations", "classification": "failure", "kind": "demonstrated-attack", "severity": "significant", "status": "open", "evidence_scope": "inherited", "scope_note": "Applies to variants using the affected Intel or AMD trust roots. PAL*M excludes physical attacks. A TDX-backed safeguard claim against a physical host attacker would be defeated, but these studies do not demonstrate a break of the AWS Nitro proof-of-guardrail prototype or of verifier-side recomputation.", "related_finding": { "record": "M-0008", "flaw": 1 }, "description": "The TEE findings cover DDR5 attacks on Intel TDX, the H100 relay demonstration, DDR4 attacks on AMD SEV-SNP, and software-only SEV-SNP forgery before AMD's fixes. These are inherited hardware limits; a governance analysis explains why physical access matters in a treaty setting.", "response": "Intel and AMD place the physical attack class outside their threat models, according to the researchers. AMD reports firmware fixes for RMPocalypse.", "sources": [ "S-1202", "S-3126", "S-1210", "S-1212", "S-1213", "S-0012", "S-0014", "S-1500", "S-0018" ], "helps": [ { "by": "M-0009", "how": "A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically." } ] }, { "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" ] }, { "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" ] } ], "criticalMechanisms": [], "significantMechanisms": [ "M-0023", "M-0001", "M-0013" ], "familyContext": [], "scopeLimitations": [ { "mech": "M-0023", "n": 1, "historical": false, "title": "Attestation shows a safeguard ran, not that it is effective", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Proof of guardrail ensures that the guardrail executed, but the guardrail can still err or be jailbroken. Because the guardrail must be open source, a malicious developer can attack it with jailbreaks while still presenting a valid proof. In the authors' evaluation, Llama Guard 3 reached an F1 score of 0.56 on the unsafe class of the ToxicChat dataset. The authors state that proof of guardrail should not be interpreted or advertised as proof of safety.", "response": null, "sources": [ "S-1500" ] }, { "mech": "M-0023", "n": 2, "historical": false, "title": "Selective attestation leaves traffic uncovered", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Attestations are issued per response. In the prototype, the agent offers them when it receives high-stakes questions, so nothing shows that unattested traffic went through the same path. PAL*M's authors note that a prover could cherry-pick favourable executions, and suggest verifier-published nonces or requesting only session-level proofs. A governance analysis notes that auditors also need assurance that all activity is accounted for, since a host could start a second confidential virtual machine that bypasses monitoring.", "response": null, "sources": [ "S-1500", "S-0012", "S-0014" ], "helps": [ { "by": "M-0010", "how": "On-chip counters are a proposed route to evidence about everything a chip runs, including a second virtual machine that skips the safeguard." } ] }, { "mech": "M-0023", "n": 3, "historical": false, "title": "Measurements may omit behaviour-relevant configuration or runtime changes", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Every component that influences inference behaviour must be covered by the launch measurement, including feature flags, environment variables and invocation arguments. A launch measurement also does not show that a program keeps running as measured if the kernel is later compromised.", "response": null, "sources": [ "S-0014" ] }, { "mech": "M-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-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." } ] } ], "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-0023", "record": "M-0023", "n": 1, "historical": false, "title": "Attestation shows a safeguard ran, not that it is effective", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Proof of guardrail ensures that the guardrail executed, but the guardrail can still err or be jailbroken. Because the guardrail must be open source, a malicious developer can attack it with jailbreaks while still presenting a valid proof. In the authors' evaluation, Llama Guard 3 reached an F1 score of 0.56 on the unsafe class of the ToxicChat dataset. The authors state that proof of guardrail should not be interpreted or advertised as proof of safety.", "response": null, "sources": [ "S-1500" ] }, { "mech": "M-0023", "record": "M-0023", "n": 2, "historical": false, "title": "Selective attestation leaves traffic uncovered", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Attestations are issued per response. In the prototype, the agent offers them when it receives high-stakes questions, so nothing shows that unattested traffic went through the same path. PAL*M's authors note that a prover could cherry-pick favourable executions, and suggest verifier-published nonces or requesting only session-level proofs. A governance analysis notes that auditors also need assurance that all activity is accounted for, since a host could start a second confidential virtual machine that bypasses monitoring.", "response": null, "sources": [ "S-1500", "S-0012", "S-0014" ], "helps": [ { "by": "M-0010", "how": "On-chip counters are a proposed route to evidence about everything a chip runs, including a second virtual machine that skips the safeguard." } ] }, { "mech": "M-0023", "record": "M-0023", "n": 3, "historical": false, "title": "Measurements may omit behaviour-relevant configuration or runtime changes", "classification": "scope-limitation", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "Every component that influences inference behaviour must be covered by the launch measurement, including feature flags, environment variables and invocation arguments. A launch measurement also does not show that a program keeps running as measured if the kernel is later compromised.", "response": null, "sources": [ "S-0014" ] }, { "mech": "M-0023", "record": "M-0023", "n": 4, "historical": false, "title": "Components outside the attested boundary", "classification": "failure", "kind": "theoretical-argument", "severity": "significant", "status": "open", "evidence_scope": null, "scope_note": null, "related_finding": null, "description": "In the proof-of-guardrail experiments, the guardrail model and the agent's backend model were both reached through external APIs, and the authors leave the decision to trust those APIs to the verifier. The measured wrapper must also have no vulnerability that lets the unmeasured agent bypass the guardrail, for example by executing arbitrary commands inside the enclave. The code's README states that the enclave does not currently restrict the agent's arbitrary command execution, which could be used to bypass guardrails.", "response": null, "sources": [ "S-1500", "S-1501" ] }, { "mech": "M-0023", "record": "M-0023", "n": 5, "historical": false, "title": "Memory-bus interposition extracts attestation keys and forges attestations", "classification": "failure", "kind": "demonstrated-attack", "severity": "significant", "status": "open", "evidence_scope": "inherited", "scope_note": "Applies to variants using the affected Intel or AMD trust roots. PAL*M excludes physical attacks. A TDX-backed safeguard claim against a physical host attacker would be defeated, but these studies do not demonstrate a break of the AWS Nitro proof-of-guardrail prototype or of verifier-side recomputation.", "related_finding": { "record": "M-0008", "flaw": 1 }, "description": "The TEE findings cover DDR5 attacks on Intel TDX, the H100 relay demonstration, DDR4 attacks on AMD SEV-SNP, and software-only SEV-SNP forgery before AMD's fixes. These are inherited hardware limits; a governance analysis explains why physical access matters in a treaty setting.", "response": "Intel and AMD place the physical attack class outside their threat models, according to the researchers. AMD reports firmware fixes for RMPocalypse.", "sources": [ "S-1202", "S-3126", "S-1210", "S-1212", "S-1213", "S-0012", "S-0014", "S-1500", "S-0018" ], "helps": [ { "by": "M-0009", "how": "A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically." } ] }, { "mech": "M-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" ] }, { "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" ] } ], "possible_additions": [ { "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-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": "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": "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-0009", "title": "Hardware-enabled guarantees (flexHEG) and guarantee processors", "url": "https://trustbutveri.fyi/mechanisms/flexheg-guarantee-processors/", "readiness": "R1", "development_status": { "code": "R1", "label": "Proposed", "short": "Proposed", "rank": 1, "legacy_code": "R1" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 1, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1204", "S-0057" ] }, { "n": 2, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1204" ] }, { "n": 4, "severity": "significant", "status": "open", "evidence_scope": "unassessed", "sources": [ "S-1204" ] } ], "open_failures": { "critical": 0, "significant": 3, "minor": 0 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "flaw", "mech": "M-0023", "n": 5, "title": "Memory-bus interposition extracts attestation keys and forges attestations", "severity": "significant", "how": "A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically." } ] }, { "id": "M-0012", "title": "Hardware-attested weight binding", "url": "https://trustbutveri.fyi/mechanisms/model-identity-attestation/", "readiness": "R3", "development_status": { "code": "R3", "label": "Operational use", "short": "Operational use", "rank": 3, "legacy_code": "R3" }, "security_evidence": { "attack_testing": { "status": "independent-red-team", "label": "Published attack testing", "kind": "practical", "attribution": "Independent team" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 1, "severity": "critical", "status": "open", "evidence_scope": "inherited", "sources": [ "S-1202", "S-1210", "S-1212", "S-1213", "S-1206", "S-0012" ], "related_finding": { "record": "M-0008", "flaw": 1 } }, { "n": 2, "severity": "significant", "status": "mitigated", "evidence_scope": "unassessed", "sources": [ "S-0013", "S-0014" ] } ], "open_failures": { "critical": 1, "significant": 0, "minor": 0 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "blocker", "mech": "M-0023", "text": "Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation." } ] }, { "id": "M-0008", "title": "TEE remote attestation for AI workloads", "url": "https://trustbutveri.fyi/mechanisms/tee-remote-attestation/", "readiness": "R3", "development_status": { "code": "R3", "label": "Operational use", "short": "Operational use", "rank": 3, "legacy_code": "R3" }, "security_evidence": { "attack_testing": { "status": "independent-red-team", "label": "Published attack testing", "kind": "practical", "attribution": "Independent team" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 1, "severity": "critical", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-1202", "S-3126", "S-0012", "S-1206", "S-0014", "S-1210", "S-1212", "S-3127" ] }, { "n": 2, "severity": "critical", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-1210", "S-1211" ] }, { "n": 3, "severity": "critical", "status": "mitigated", "evidence_scope": "mechanism", "sources": [ "S-1212", "S-1213", "S-3127", "S-3128" ] }, { "n": 4, "severity": "significant", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-1202" ] }, { "n": 5, "severity": "significant", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-0012", "S-0009", "S-0014", "S-3123", "S-3129" ] }, { "n": 8, "severity": "significant", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-0014", "S-0009", "S-3130", "S-3131" ] } ], "open_failures": { "critical": 2, "significant": 3, "minor": 0 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "blocker", "mech": "M-0023", "text": "Frontier model inference typically needs several GPUs, GPU confidential computing is less mature than CPU support, and CPU inference, which an enclave prototype had to use, ran about 100 times slower than GPU inference." }, { "kind": "blocker", "mech": "M-0023", "text": "Trust rests on a small number of hardware vendors, and a per-CPU Intel attestation key has been extracted by physical attack." } ] }, { "id": "M-0017", "title": "Tamper evidence for verifier devices", "url": "https://trustbutveri.fyi/mechanisms/tamper-evidence-for-verifier-devices/", "readiness": "R2", "development_status": { "code": "R2", "label": "Research demonstration", "short": "Research demo", "rank": 2, "legacy_code": "R2" }, "security_evidence": { "attack_testing": { "status": "analysis", "label": "Published security analysis", "kind": "analysis" }, "independent_evaluation": { "status": "unassessed" }, "formal_proof": { "status": "unassessed" }, "deployment_assurance": { "status": "unassessed" }, "legacy_evaluation_code": null, "scoped_findings": [ { "n": 1, "severity": "significant", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-1317", "S-1318" ] }, { "n": 3, "severity": "significant", "status": "open", "evidence_scope": "mechanism", "sources": [ "S-1315", "S-0052", "S-3261" ] } ], "open_failures": { "critical": 0, "significant": 2, "minor": 0 } }, "fits_filters": true, "filter_issues": [], "reasons": [ { "kind": "blocker", "mech": "M-0013", "text": "Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them." } ] }, { "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-0023" ] }, { "id": "M-0012", "neededBy": [ "M-0023" ] }, { "id": "M-0002", "neededBy": [ "M-0013" ] }, { "id": "M-0017", "neededBy": [ "M-0013" ] }, { "id": "M-0022", "neededBy": [ "M-0013" ] } ], "shared": [], "blockers": [ { "mech": "M-0023", "n": 1, "historical": false, "text": "No published design shows that all of a provider's traffic passes through the attested safeguard path; current evidence covers individual attested responses.", "theme": "coverage-hidden-compute", "blocked_by": null, "sources": [ "S-1500", "S-0014" ], "inProposal": null }, { "mech": "M-0023", "n": 2, "historical": false, "text": "Frontier model inference typically needs several GPUs, GPU confidential computing is less mature than CPU support, and CPU inference, which an enclave prototype had to use, ran about 100 times slower than GPU inference.", "theme": "performance-compatibility", "blocked_by": "M-0008", "sources": [ "S-0014", "S-0009" ], "inProposal": false }, { "mech": "M-0023", "n": 3, "historical": false, "text": "Trust rests on a small number of hardware vendors, and a per-CPU Intel attestation key has been extracted by physical attack.", "theme": "hardware-trust", "blocked_by": "M-0008", "sources": [ "S-0014", "S-1202" ], "inProposal": false }, { "mech": "M-0023", "n": 4, "historical": false, "text": "Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation.", "theme": "evidence-binding", "blocked_by": "M-0012", "sources": [ "S-0009", "S-0013" ], "inProposal": false }, { "mech": "M-0023", "n": 5, "historical": false, "text": "No independent red-team or audit of a safeguard-attestation system has been published, and the available prototypes are described by their authors as proofs of concept that have not been stress-tested by a counterparty.", "theme": "adversarial-validation", "blocked_by": null, "sources": [ "S-1501", "S-1504" ], "inProposal": null }, { "mech": "M-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 }, { "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": false }, { "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 } ] }, "exposure": { "weights": { "shown": [], "partial": [ "M-0023", "M-0001", "M-0013" ], "hidden": [], "none": [], "unknown": [] }, "io": { "shown": [], "partial": [ "M-0023", "M-0001", "M-0013" ], "hidden": [], "none": [], "unknown": [] }, "training": { "shown": [], "partial": [ "M-0013" ], "hidden": [], "none": [ "M-0023", "M-0001" ], "unknown": [] } }, "implementations": [ { "mechanism": "M-0023", "selected": null, "implementations": [] }, { "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/" } ] }, { "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/" } ] } ], "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-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-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-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-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-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-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-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/" } ] }