Proposal Explorer
ResetA verification proposal from the AI Verification Tech Map, from its records of 2026-10-09. https://trustbutveri.fyi/explorer/?mechanisms=M-0022,M-0016&hide=weights&cols=claims,tested,hardware
Analysis
Applied filters: Keep hidden from the verifier: model weights. Not set (Any): Prover, Verifier devices on site, Prover cooperation, Chips, Minimum development status, Attack testing.
Overview
| Mechanism | Development | Security evidence | Open failures | Attack testing | Hardware |
|---|---|---|---|---|---|
| Side-channel suppression for isolated facilities | Proposed | Published security analysis | none | Analysis | Retrofit device |
| Timed challenge-response and memory-occupation challenges | Research demo | Published security analysis | 1 significant | Analysis | None |
- Open failures: n critical n significant n minor
Claim coverageNo claims yet
Add claims to see which ones the mechanisms address.
Properties2 built for an adversarial prover
- Built for an adversarial prover
- Side-channel suppression for isolated facilities and Timed challenge-response and memory-occupation challenges
- No new hardware needed
- Timed challenge-response and memory-occupation challenges
Attack testing2 mechanisms with published testing
Attack testing records published testing for this use. It does not by itself show independent review, a formal proof or that a deployed system is secure.
Limits1 scope limitation · 3 open questions · 1 not yet demonstrated · 1 mechanism with open significant failures
- Open significant failures
1 failure in 1 mechanism
Remote memory narrows the timing margin in Timed challenge-response and memory-occupation challenges
Data-centre remote memory access returns in about 1–2 µs, against about 70–200 ns for local DRAM. The MIRI overview says verification of memory saturation depends on ruling out remote access by latency or physical disconnection. It names pre-staging data into local memory as the remaining evasion and proposes an unpredictable, capacity-filling challenge to close it. 2
Known failure · Theoretical argument · Significant · Open. On the record
Related mechanism Research demo Bandwidth limits and compartmentalization: Physical disconnection is proposed to exclude remote memory between the separated groups during a challenge. It depends on the isolation boundary being enforced. A pointer, not evidence that this failure is mitigated. Add
- Scope limitations
Openings for airflow, power and optics weaken shielding in Side-channel suppression for isolated facilities
Cankaya notes that keeping attenuation high while passing high-power airflow, cabling and optical links adds complexity beyond existing shielded-enclosure specifications. 1
Scope limitation · Theoretical argument. On the record
- Open questions
Supply-chain implants may evade inspection in Side-channel suppression for isolated facilities
Cankaya identifies malicious hardware embedded deep in purchased components as a residual risk that visual inspection and disassembly may not catch. He notes that radiographic examination under high-security standards could mitigate it. 1
Open question · Theoretical argument. On the record
Inspection assumptions may not hold in Side-channel suppression for isolated facilities
The design's statistical argument assumes that visual or disassembly inspection catches every flaw that is present in a sampled unit. Cankaya is unsure whether destructive teardowns are defence-dominant or offence-dominant. 1
Open question · Open question. On the record
Error rates not quantified in Timed challenge-response and memory-occupation challenges
Monfared et al. show separable timing distributions. Their acceptance rule passes a GPU when its mean time per round stays at or below a chosen maximum, and an appendix outlines statistical tests for the proof-of-work puzzle. They leave hardware-specific threshold values to future work and report no false-positive or false-negative rates. 4
Open question · Open question. On the record
- Not yet demonstrated
- Proposed Side-channel suppression for isolated facilities
Possible additions1 for open failures · 1 for dependencies
Mechanisms on the map that are not in the proposal. Pointers, not recommendations.
-
- Bears on the open significant failure “Remote memory narrows the timing margin” in Timed challenge-response and memory-occupation challenges. Physical disconnection is proposed to exclude remote memory between the separated groups during a challenge. It depends on the isolation boundary being enforced.
- Timed challenge-response and memory-occupation challenges waits on it. Outside help, such as remote memory, must be excluded during challenges.
Dependencies5 blockers
- Blockers
5 blockers recorded
- Side-channel suppression for isolated facilities
- Timed challenge-response and memory-occupation challenges
- No network-level memory challenge across data-centre servers has been demonstrated. Adversarial validation 2
- Challenges that fill memory displace workloads; filling a pod's volatile memory takes tens of minutes and SSDs take hours. Performance & compatibility 2 4
- Outside help, such as remote memory, must be excluded during challenges. Coverage & hidden compute. Waits on Bandwidth limits and compartmentalization 2
What the verifier seesNo outright disclosure specified
From the family or selected implementation's record.
- Model weights
Not involved: Side-channel suppression for isolated facilities and Timed challenge-response and memory-occupation challenges.
- Inputs and outputs
Not involved: Side-channel suppression for isolated facilities and Timed challenge-response and memory-occupation challenges.
- Training data
Not involved: Side-channel suppression for isolated facilities and Timed challenge-response and memory-occupation challenges.
Exposure notes
- Side-channel suppression for isolated facilities: Shields and filters a facility; it does not handle model data.
- Timed challenge-response and memory-occupation challenges: Uses verifier-chosen challenges; it does not handle model data.
Implementations7 systems
- Side-channel suppression for isolated facilities
- Proposed AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
- Proposed Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
- Proposed RAND secure inference data center (SIDC) design Proposed architecture, RAND
- Timed challenge-response and memory-occupation challenges
- Proposed Data-centre memory challenging Proposed architecture, Machine Intelligence Research Institute
- Research demo GPU contention probes Research prototype
- Proposed Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
- Research demo SAGE Research prototype
- Research demo VRAM-residency challenge Research prototype
Sources11 cited
- Suppressing Side Channels in an Untrusted Data Center via Retrofitted Defenses, N. Cankaya (2026). Original
- A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
- Verification Plan, R. Dean (2026). Original
- Timing and Memory Telemetry on GPUs for AI Governance, S. K. Monfared et al. (2026). Original
- SAGE: Software-based Attestation for GPU Execution, A. Ivanov et al. (2023). Original
- SWATT: SoftWare-based ATTestation for Embedded Devices, A. Seshadri et al. (2004). Original
- Proofs of Space, S. Dziembowski et al. (2015). Original
- Secure Code Update for Embedded Devices via Proofs of Secure Erasure, D. Perito & G. Tsudik (2010). Original
- Software-Based Memory Erasure with Relaxed Isolation Requirements, S. Bursuc et al. (2024). Original
- On the Difficulty of Software-Based Attestation of Embedded Devices, C. Castelluccia et al. (2009). Original
- Refutation of "On the Difficulty of Software-Based Attestation of Embedded Devices", A. Perrig & L. van Doorn (2010). Original
Share the link to this proposal. This proposal is also available as plain text and JSON.
Filter mechanisms
Filters apply to mechanisms only. They describe the setting a proposal is for, and all are off by default. A mechanism that a filter rules out is flagged and does not count towards claim coverage. Selected implementations use their own record fields. A match means not excluded; conditional or unspecified exposure stays with a note. Passing a filter does not establish that the assumptions hold in a deployment.
24 of 25 mechanisms match · Clear all
Prover
How far can the party being checked be trusted?
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.
Keeps mechanisms whose threat model holds against at least this prover. Adversarial is the strongest assumption. Definitions
Verifier devices on site
May the verifier install its own hardware at the prover's sites?
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.
"Not allowed" removes mechanisms that need a retrofit device, such as a network tap or a sealed sensor. Definitions
Prover cooperation
How much must the prover take part?
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.
"Partial at most" removes mechanisms that need the prover's active participation. "Not required" keeps only those that work without it. Definitions
Chips
May the proposal depend on new chip designs?
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.
"Existing chips only" removes mechanisms that need changes to future chip designs. Definitions
Minimum development status
Development status
A level describes the public evidence for a mechanism's stated use, not its cost or feasibility. R3 can still have open critical flaws.
Keeps mechanisms whose readiness level is at least this one. Definitions
Attack testing
How hard has each mechanism been attacked in public?
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.
Keeps mechanisms whose strongest published attack testing is at least this. Definitions
Keep hidden from the verifier
What must the verifier never see? Choose any.
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.
Removes mechanisms that show the asset to the verifier. Conditional or unspecified exposure stays with a note and needs checking against the privacy requirement.
Claims
A claim is something one party wants to verify about another party's AI hardware or software. Each claim's number shows how the proposal addresses it.
- 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.
Addressed means a mechanism in the proposal is aimed at the claim and is not excluded by your filters. It does not mean the claim is verified: check its assessed use, development status, security evidence, assumptions and findings.
Mechanisms
A mechanism is a general technique for verifying claims. Its badge is its development status for its stated use. An optional implementation choice narrows its assumptions, assessed use and claim links to that record. Lines join it to the claims it addresses. Click a line for details.Under its name it lists the claims it is aimed at or supports.
- Aimed at the claim: verifying it is a direct purpose of the mechanism.
- Supports the claim: helps verify it without being aimed at it.
- Faint: excluded by your filters, so it does not count towards claim coverage.
Overview
One row per mechanism in the proposal. Every mark comes from that mechanism's record, as listed in the panels below; what the verifier sees is the editors' reading of the record's text. Failure counts are per mechanism. Summary counts name mechanisms with open failures, not a sum of attacks. Choosing an implementation narrows each row to that record's assessed use; family findings remain as context. Findings are grouped as known failures, scope limitations and open questions. Only known failures count as failures. Counts are an inventory of published findings, not a risk score.
What the verifier sees
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.
Possible additions
Mechanisms on the map, not in the proposal, that the records connect to an unaddressed or partly addressed claim, an open failure or a dependency. They are pointers, not recommendations: each brings its own readiness level and findings, and none is claimed to close a failure. Links from failures are the editors' reading of the two records.
Start from a goal
A goal is something a rule or agreement about AI sets out to achieve. Choosing one loads the claims it needs verified. Your mechanisms and filters stay as they are.
- Cap frontier training2 direct, 3 supportingKeep every AI training run below an agreed amount of compute.
- Pause frontier AI development2 direct, 3 supportingStop new AI training runs and experiments for an agreed period, while existing models stay in service.
- Deploy only evaluated models2 direct, 3 supportingDeploy powerful AI models widely only after their risks have been evaluated and judged manageable.
- Prevent catastrophic misuse2 direct, 2 supportingKeep capable AI models from helping anyone carry out catastrophic attacks, such as biological or chemical ones.
- Prevent weight theft1 direct, 1 supportingKeep the weights of capable AI models from being copied out of the facilities that hold them.
- Enforce chip export controls1 directKeep export-controlled AI chips at the destinations they were authorised for.
Start from a published design
Choosing a design loads the mechanisms its record realises or depends on. If the proposal has no claims yet, it also loads the claims that record says the design addresses.
- AI 2040 inference-only verification stack7 mechanismsProposed architecture, AI Futures Project
- Low-trust AI compute verification system overview7 mechanismsProposed architecture, Machine Intelligence Research Institute
- RAND secure inference data center (SIDC) design2 mechanismsProposed architecture, RAND