Proposal Explorer

Add claims to see which ones the mechanisms address.

In production

• R3 Model identity attestation for showing users that a service runs the declared model weights

Built for an adversarial prover

Network taps and certifiers

No new hardware needed

Model identity attestation

Flaws since mitigated

• Launch-state attestation does not by itself cover weights loaded later in Model identity attestation ^{3 15}
• Verifier dictionary attacks on hashes in Network taps and certifiers ¹⁷

Published attempts to break a system, including those that found failures. Testing history does not show that open flaws are resolved.

• Side-channel suppression for isolated facilities, RAND secure inference data center (SIDC) design: Analysis
• Model identity attestation: Independent red-team
• Network taps and certifiers: Analysis

Open critical flaws

• Underlying attestation can be forged or relayed in Model identity attestation

  Critical for the enclave route against an operator with physical access to affected hardware, or control of an unpatched SEV-SNP hypervisor. It does not apply to the recomputation route. PAL*M excludes physical attacks, and Tinfoil acknowledges this boundary.

  The enclave route inherits the platform-specific TEE attestation failures. Intel TDX forgery and H100 relay were demonstrated with physical access and host control. Battering RAM defeated AMD SEV-SNP attestation on DDR4 servers; RMPocalypse did so from malicious host software on platforms without AMD's fixes. These demonstrate failures of the trust roots, not of each model-commitment protocol. ^{4 6 10 12 13 14}

  Response: The TEE.fail authors report that physical interposer attacks are outside Intel's and AMD's threat models. AMD reports fixes for RMPocalypse.

  Demonstrated attack · Critical · Open · Inherited finding. On the record · Related finding in TEE remote attestation for AI workloads

  Related mechanism R1 Hardware-enabled guarantees (flexHEG) and guarantee processors: A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically. A pointer, not evidence that this flaw is mitigated. Add

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

Open significant flaws

8 flaws in 3 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

• For private models, a user can confirm consistency but not content in Model identity attestation

  When weights are not published, users can check that the same root hash is served each time, but not what the model is. Pairing the hash with an attested evaluation, as in Attestable Audits, is one proposed remedy. ^{3 16}

  Open question · Significant · Open. On the record

• Recomputation depends on trusted logging and randomness, and its tolerance leaves a covert channel in Model identity attestation

  The recomputation variant assumes that every input, output and seed is logged correctly, and that the attacker can neither predict nor manipulate which messages are sampled for verification. Legitimate nondeterminism concentrates at a few token positions, and slow leaks within the tolerated slack remain possible. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token, reducing the exfiltration slowdown from 146–254 times under benign prompts to 60–118 times. The attack targets the exfiltration bound, not the check that outputs match the declared model. ^{5 11}

  Demonstrated attack · Significant · Open. On the record

  Related mechanism R1 Network taps and certifiers: Taps are proposed to copy and hash traffic on the monitored links, reducing reliance on the prover's own log. This still depends on the monitored boundary and trusted capture. A pointer, not evidence that this flaw is mitigated. In the proposal.

  Related mechanism R3 Deterministic and bit-exact inference: Bit-exact inference would remove the numerical tolerance that leaves this channel. A pointer, not evidence that this flaw is mitigated. Add

• Output nondeterminism leaves covert capacity in Network taps and certifiers

  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. ^{11 17}

  Theoretical argument · Significant · Open. On the record

  Related mechanism R3 Deterministic and bit-exact inference: Deterministic replay is one of the two remedies the flaw's source names. A pointer, not evidence that this flaw is mitigated. Add

  Related mechanism R2 Bounding unexplained information in outputs: Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict. A pointer, not evidence that this flaw is mitigated. Add

• Some links cannot be passively tapped in Network taps and certifiers

  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. ^{18 25}

  Open question · Significant · Open. On the record

• Encrypted fabrics hide plaintext from both parties in Network taps and certifiers

  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. ¹⁸

  Open question · Significant · Open. On the record

• Residual side channels in simple passive setups in Network taps and certifiers

  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. ²¹

  Theoretical argument · Significant · Open. On the record

• Completeness rests on physical monitoring left out of scope in Network taps and certifiers

  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. ¹⁷

  Open question · Significant · Open. On the record

  Related mechanism R1 Side-channel suppression for isolated facilities: Addresses the radio, power-line and thermal channels that network-level designs leave out. A pointer, not evidence that this flaw is mitigated. In the proposal.

Open minor flaws

1 mechanism 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

Not yet demonstrated

R1 Side-channel suppression for isolated facilities and R1 Network taps and certifiers

Mechanisms on the map that are not in the proposal. Pointers, not recommendations. ?

• R1 Hardware-enabled guarantees (flexHEG) and guarantee processors Add
  • Bears on the open critical flaw “Underlying attestation can be forged or relayed” in Model identity attestation. A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically.
• R3 Deterministic and bit-exact inference Add
  • Bears on the open significant flaw “Recomputation depends on trusted logging and randomness, and its tolerance leaves a covert channel” in Model identity attestation. Bit-exact inference would remove the numerical tolerance that leaves this channel.
  • Bears on the open significant flaw “Output nondeterminism leaves covert capacity” in Network taps and certifiers. Deterministic replay is one of the two remedies the flaw's source names.
  • Model identity attestation waits on it. Numerical nondeterminism limits how tightly recomputation can pin down the model and sampling.
  • Network taps and certifiers waits on it. Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove.
• R2 Bounding unexplained information in outputs Add
  • Bears on the open significant flaw “Output nondeterminism leaves covert capacity” in Network taps and certifiers. Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict.
• R3 TEE remote attestation for AI workloads Add
  • Model identity attestation waits on it. Attestation that resists physical attackers, for the enclave variant.
• R2 Tamper evidence for verifier devices Add
  • Network taps and certifiers waits on it. Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them.
• R3 Sampled inference recomputation Add
  • Network taps and certifiers depends on it.

Missing prerequisites

• R3 Sampled inference recomputation needed by Network taps and certifiers Add
• R3 Deterministic and bit-exact inference needed by Network taps and certifiers Add
• R2 Tamper evidence for verifier devices needed by Network taps and certifiers Add

Shared foundations

• Deterministic and bit-exact inference relied on by Model identity attestation and Network taps and certifiers

Blockers

12 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
• Model identity attestation
  • Attestation that resists physical attackers, for the enclave variant. Hardware trust. Waits on TEE remote attestation for AI workloads ¹⁰
  • Numerical nondeterminism limits how tightly recomputation can pin down the model and sampling. Protocol soundness. Waits on Deterministic and bit-exact inference ⁵
  • The recomputation variant needs the verifier to hold the declared weights. Access & governance ⁵
• Network taps and certifiers
  • 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. Performance & compatibility ^{25 26}
  • Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove. Evidence binding. Waits on Deterministic and bit-exact inference ¹⁷
  • Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them. Hardware trust. Waits on Tamper evidence for verifier devices ^{17 19}
  • Radio, power-line and thermal channels are not addressed by network-level designs. Coverage & hidden compute. Waits on Side-channel suppression for isolated facilities ¹⁷
  • Red-teaming by specialists is called for but has not been reported. Adversarial validation ¹⁷

From the family or selected implementation's record. ?

Model weights

Depends on the design for Model identity attestation and Network taps and certifiers.

Unspecified for Side-channel suppression for isolated facilities. Check the implementation record.

Inputs and outputs

Depends on the design for Model identity attestation and Network taps and certifiers.

Unspecified for Side-channel suppression for isolated facilities. Check the implementation record.

Training data

Depends on the design for Network taps and certifiers.

Not involved: Model identity attestation.

Unspecified for Side-channel suppression for isolated facilities. Check the implementation record.

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

Model identity attestation

• R2 Attestable Audits Research prototype, University of Cambridge
• R2 PAL*M Research prototype, University of Waterloo
• R3 Tinfoil model identity (Modelwrap) Product, Tinfoil

Network taps and certifiers

• 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 SASH confidential network logger Research prototype, Singapore AI Safety Hub (SASH)

1. Highly Secure Inference Data Centers: A Vertically Integrated Strategy for Security Engineering, S. F. Comer et al. (2026). Original
2. Suppressing Side Channels in an Untrusted Data Center via Retrofitted Defenses, N. Cankaya (2026). Original
3. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). Original
4. PAL*M: Property Attestation for Large Generative Models, P. Chantasantitam et al. (2026). Original
5. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
6. A primer on secure enclaves, Tinfoil (2026). Original
7. Backend infrastructure, Tinfoil (2026). Original
8. How verification works in Tinfoil, Tinfoil (2026). Original
9. modelwrap: Reproducible dm-verity read-only image of Huggingface models, Tinfoil (2026). Original
10. TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition, J. Chuang et al. (2026). Original
11. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
12. Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing, J. De Meulemeester et al. (2026). Original
13. RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP, B. Schlüter & S. Shinde (2025). Original
14. SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020), AMD (2025). Original
15. On TEEs for Privacy-Preserving Monitoring in AI Governance, Gloria Z (2026). Original
16. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). Original
17. Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors, N. Cankaya et al. (2026). Original
18. The Fundamentals and Feasibility of Secure Network Taps for Verifying AI Datacenter Use, N. Cankaya (2026). Original
19. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
20. Verification Plan, R. Dean (2026). Original
21. Fitting a Network TAP to our Inference Verification Prototype, Amodo Design (2026). Original
22. Amodo-Design/Inference-Recomputation-Prototype (GitHub repository), Amodo Design (2026). Original
23. inference-verification: Inference Verification Prototype, Singapore AI Safety Hub (SASH) (2026). Original
24. Internationalising AI Verification, Singapore AI Safety Hub (SASH) (2026). Original
25. Network Tapping for AI Verification: A Technical Assessment, Amodo Design (2026). Original
26. Network Traffic Hashing, Amodo Design (2026). Original