Proposal Explorer
ResetA verification proposal from the AI Verification Tech Map, from its records of 2026-10-08. https://trustbutveri.fyi/explorer/?mechanisms=M-0022,M-0016&implementations=M-0022:I-0010,M-0016:I-0012
Analysis
Applied filters: none. Every filter is set to Any.
Overview
| Mechanism | Readiness | Open flaws |
|---|---|---|
| Side-channel suppression for isolated facilitiesRAND secure inference data center (SIDC) design | R1 | 1 significant1 minorFamily context below |
| Timed challenge-response and memory-occupation challengesLow-trust AI compute verification system overview | R1 | 2 significant1 minorFamily context below |
- Open flaws: n critical n significant n minor
Claim coverageNo claims yet
Add claims to see which ones the mechanisms address.
Properties1 built for an adversarial prover
- Built for an adversarial prover
- Timed challenge-response and memory-occupation challenges
Attack testing2 mechanisms with published testing
Published attempts to break a system, including those that found failures. Testing history does not show that open flaws are resolved.
Limits2 families with findings to check · 2 not yet demonstrated · 2 mechanisms with open significant findings
- Family findings
- Side-channel suppression for isolated facilities
Context for RAND secure inference data center (SIDC) design. These findings concern the family or other implementations; applicability must be checked against their stated scope.
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. 2
Theoretical argument · Significant · Open. On the record
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. 2
Theoretical argument · Significant · Open. 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. 2
Open question · Significant · Open. On the record
- Timed challenge-response and memory-occupation challenges
Context for Low-trust AI compute verification system overview. These findings concern the family or other implementations; applicability must be checked against their stated scope.
Timing-based software attestation has been broken in practice in Timed challenge-response and memory-occupation challenges
Castelluccia et al. implemented two generic attacks, one based on a return-oriented rootkit and one on code compression, together with specific attacks on SWATT and ICE-based schemes, on commodity sensor nodes. They conclude that secure time-based attestation is "very difficult, if not impossible, to design correctly". The attacks target embedded schemes, not AI accelerators. 5 6
Response: Perrig and van Doorn, two of the designers of SWATT and ICE, replied in August 2010. They argue that the rootkit attack defeats a naive implementation, not a property the schemes claim, and that the SWATT attack was run on a re-implementation on a chip with eight times the program memory, where SWATT's own chip is almost always full of code. They accept that the attack on ICE works.
Demonstrated attack · Significant · Disputed. On the record
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 adds that pre-staging data is ruled out only by unpredictable, capacity-filling challenges. 3
Theoretical argument · Significant · Open. On the record
Related mechanism R2 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 flaw is mitigated. Add
Error rates not quantified in Timed challenge-response and memory-occupation challenges
Monfared et al. show separable timing distributions but do not define thresholds or statistical tests, so false-positive and false-negative rates are not quantified. 7
Open question · Minor · Open. On the record
- Side-channel suppression for isolated facilities
- Open significant flaws
3 flaws in 2 mechanisms
Everything rests on the trusted setup in RAND secure inference data center (SIDC) design
Reference measurements for model weights and reference data are established in a trusted setup phase. The report states that the system cannot detect compromise that happened before ingestion if the trusted setup itself is compromised. 1
Theoretical argument · Significant · Open. On the record
Mismatches cannot be attributed to cheating or error in Low-trust AI compute verification system overview
A failed hash or replay does not show whether it came from an evasion attempt, a random bit flip or an evaluation error. The author notes that if detected anomalies can plausibly be waved off as malfunctions, deterrence becomes less effective, so the parties need an agreed escalation procedure that ends in attribution. 3
Theoretical argument · Significant · Open. On the record
Inspector agents may be manipulable in Low-trust AI compute verification system overview
Automated compliance screening with LLM-based inspector agents must resist prompt-injection attacks. Adversarially trained systems might hide malicious actions with steganography, which makes backdoor detection an open problem. 3
Open question · Significant · Open. On the record
- Open minor flaws
2 mechanisms with minor findings
Security weakens over long operation in RAND secure inference data center (SIDC) design
The authors claim that the facility can withstand attacks at the OC5 level for a five-year operational period. They expect its ability to withstand long OC5 campaigns to become less robust the longer the facility remains in operation. 1
Theoretical argument · Minor · Open. On the record
Deliberate faults leak a bit each in Low-trust AI compute verification system overview
A malicious device can leak one bit by deliberately outputting a wrong result, which blocks a disclosure when the cross-comparison fails. The design therefore needs a pre-agreed budget of tolerated faults. 3
Theoretical argument · Minor · Open. On the record
Possible additions4 for dependencies
Mechanisms on the map that are not in the proposal. Pointers, not recommendations.
-
- Timed challenge-response and memory-occupation challenges waits on it. Exact replay needs complete hardware and software metadata, and the tolerable slowdown from emulation is an open question.
-
- Timed challenge-response and memory-occupation challenges waits on it. Tamper-evident, rapidly mass-manufacturable and retrofittable enclosures for side-channel defence are an open research question, and physical security against covert communication in every monitored data centre is challenging.
-
- Timed challenge-response and memory-occupation challenges waits on it. Empirical feasibility of passive optical splitting at 53–112 GBaud under realistic conditions is an open question.
-
- Side-channel suppression for isolated facilities depends on it.
Dependencies3 missing prerequisites · 10 blockers
- Missing prerequisites
- R3 Model identity attestation needed by Side-channel suppression for isolated facilities Add
- R1 Network taps and certifiers needed by Timed challenge-response and memory-occupation challenges Add
- R3 Deterministic and bit-exact inference needed by Timed challenge-response and memory-occupation challenges Add
- Blockers
10 blockers recorded
- Side-channel suppression for isolated facilities
- No prototype exists; RAND recommends prototyping key security features and integration now. Adversarial validation 1
- The report describes internal integrity checks, audit logging and accreditation, but no way for a party outside the operator to verify the facility's properties. Access & governance 1
- Human review of every prompt and response makes each request take three to five minutes, with the review steps as the rate-limiting factor. Performance & compatibility 1
- Detailed design information is withheld from the public report and is to be evaluated privately with stakeholders, which limits independent public scrutiny. Access & governance 1
- Timed challenge-response and memory-occupation challenges
- Empirical feasibility of passive optical splitting at 53–112 GBaud under realistic conditions is an open question. Performance & compatibility. Waits on Network taps and certifiers 3
- Exact replay needs complete hardware and software metadata, and the tolerable slowdown from emulation is an open question. Performance & compatibility. Waits on Deterministic and bit-exact inference 3
- Tamper-evident, rapidly mass-manufacturable and retrofittable enclosures for side-channel defence are an open research question, and physical security against covert communication in every monitored data centre is challenging. Hardware trust. Waits on Tamper evidence for verifier devices 3
- A mass-manufacturable, good-enough side-channel defence, particularly power-line filtering, has not been constructed or red-teamed. Coverage & hidden compute. Waits on Side-channel suppression for isolated facilities 3
- Distinguishing one server's DRAM contents from another's by challenge-response timing, and a general challenge-response protocol for diverse data types, are open. Coverage & hidden compute. Waits on Timed challenge-response and memory-occupation challenges 3
- The threat model is under-developed and needs input from cybersecurity and AI threat-modelling experts. Adversarial validation 3
- Side-channel suppression for isolated facilities
What the verifier sees2 unspecified
From the family or selected implementation's record.
- Model weights
Unspecified for Side-channel suppression for isolated facilities and Timed challenge-response and memory-occupation challenges. Check the implementation record.
- Inputs and outputs
Unspecified for Side-channel suppression for isolated facilities and Timed challenge-response and memory-occupation challenges. Check the implementation record.
- Training data
Unspecified for Side-channel suppression for isolated facilities and Timed challenge-response and memory-occupation challenges. Check the implementation record.
Exposure notes
- Side-channel suppression for isolated facilities, RAND secure inference data center (SIDC) design: This Explorer has no asset-specific exposure assessment for this implementation. Check its source and deployment assumptions.
- Timed challenge-response and memory-occupation challenges, Low-trust AI compute verification system overview: This Explorer has no asset-specific exposure assessment for this implementation. Check its source and deployment assumptions.
Implementations7 systems
- Side-channel suppression for isolated facilities
- R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
- R1 Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
- R1 RAND secure inference data center (SIDC) design Proposed architecture, RAND
- Timed challenge-response and memory-occupation challenges
- R1 Data-centre memory challenging Proposed architecture, Machine Intelligence Research Institute
- R2 GPU contention probes Research prototype
- R1 Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
- R2 SAGE Research prototype
- R2 VRAM-residency challenge Research prototype
Sources7 cited
- Highly Secure Inference Data Centers: A Vertically Integrated Strategy for Security Engineering, S. F. Comer et al. (2026). Original
- 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
- Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors, N. Cankaya et al. (2026). 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
- Timing and Memory Telemetry on GPUs for AI Governance, S. K. Monfared et al. (2026). 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.
All 25 mechanisms match.
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 readiness
How mature must each mechanism be?
- Any (selected)25 match
- R1 Proposed25 match
- R2 Demonstrated14 match
- R3 In production4 match
- R4 Deployment-ready0 match
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, readiness, assumptions and open flaws.
Mechanisms
A mechanism is a general technique for verifying claims. Its badge is its readiness level 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. Flaw counts are per mechanism. Summary counts name mechanisms with open findings, not a sum of attacks. Choosing an implementation narrows each row to that record's assessed use; family findings remain as context.
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 flaw or a dependency. They are pointers, not recommendations: each brings its own readiness level and flaws, and none is claimed to close a flaw. Links from flaws 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) design3 mechanismsProposed architecture, RAND