Proposal Explorer

Add claims to see which ones the mechanisms address.

Not counted

Excluded by your filters: Bandwidth limits and compartmentalization and Model identity attestation

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

• Bandwidth limits and compartmentalization, RAND secure inference data center (SIDC) design: Analysis · excluded by filters
• Model identity attestation: Independent red-team · excluded by filters

Excluded by your filters

• Bandwidth limits and compartmentalization Readiness R1 is below the minimum of R4.
• Model identity attestation Readiness R3 is below the minimum of R4.

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. ^{7 9 13 15 16 17}

  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

• Bandwidth limits and compartmentalization

  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.

  • Low-communication training reduces the bandwidth training needs in Bandwidth limits and compartmentalization

    DiLoCo matched fully synchronous training on 8 workers while communicating 500 times less. Rahman writes that this family of methods theoretically allows large-scale training with less than 100 Mbps. Lucid includes these methods in its bounds, but notes that extreme activation compression, architectures with unusually small inter-layer widths, or modular paradigms could erode the margin. ^{2 3 4}

    Theoretical argument · Significant · Open. On the record

  • Operator control of pod routing collapses the bound in Bandwidth limits and compartmentalization

    Lucid's analysis finds that if the operator can freely assign pods to routers, it could dedicate a whole cell of 100 or more pods to one pipeline stage. The bound then falls to about 90–220x uncompressed and as low as about 25x with compression. The proposed mitigation, auditor-controlled random assignment that is periodically re-randomized, has not been implemented. ⁴

    Theoretical argument · Significant · Open. On the record

  • Undeclared local storage raises per-pod capacity in Bandwidth limits and compartmentalization

    More memory or storage per pod helps an adversary. Lucid requires per-pod storage to be declared, capped and physically inspected. ⁴

    Theoretical argument · Significant · Open. On the record

  • Training within one pod is not covered in Bandwidth limits and compartmentalization

    Lucid's bounds concern pre-training models larger than the pods are sized for. Training models that fit in one pod, fine-tuning and reinforcement-learning post-training within one pod are outside the modelled threat. ⁴

    Open question · Significant · Open. On the record

  • Parallel scale-up switches are hard enforcement points in Bandwidth limits and compartmentalization

    In GB200 topologies, GPUs reach GPUs in other nodes through NVSwitches without a NIC on the path. Amodo notes that limits are hard to enforce there because many switches work in parallel, so compromising one or two would bypass the limit. ⁵

    Theoretical argument · Significant · Open. On the record

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

• 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. ^{6 19}

  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. ^{8 14}

  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. Add

  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

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 Bandwidth limits and compartmentalization

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

• R1 Hardware-enabled guarantees (flexHEG) and guarantee processors Add

  Excluded by filters: readiness R1

  • 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

  Excluded by filters: readiness R3

  • 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.
  • Model identity attestation waits on it. Numerical nondeterminism limits how tightly recomputation can pin down the model and sampling.
• R1 Network taps and certifiers Add

  Excluded by filters: readiness R1

  • Bears on the open significant flaw “Recomputation depends on trusted logging and randomness, and its tolerance leaves a covert channel” in Model identity attestation. 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.
• R3 TEE remote attestation for AI workloads Add

  Excluded by filters: readiness R3

  • Model identity attestation waits on it. Attestation that resists physical attackers, for the enclave variant.

Blockers

7 blockers recorded

• Bandwidth limits and compartmentalization
  • 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 ¹³
  • Numerical nondeterminism limits how tightly recomputation can pin down the model and sampling. Protocol soundness. Waits on Deterministic and bit-exact inference ⁸
  • The recomputation variant needs the verifier to hold the declared weights. Access & governance ⁸

From the family or selected implementation's record. ?

Model weights

Depends on the design for Model identity attestation.

Unspecified for Bandwidth limits and compartmentalization. Check the implementation record.

Inputs and outputs

Depends on the design for Model identity attestation.

Unspecified for Bandwidth limits and compartmentalization. Check the implementation record.

Training data

Not involved: Model identity attestation.

Unspecified for Bandwidth limits and compartmentalization. Check the implementation record.

Bandwidth limits and compartmentalization

• R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• 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

1. Highly Secure Inference Data Centers: A Vertically Integrated Strategy for Security Engineering, S. F. Comer et al. (2026). Original
2. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). Original
3. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). Original
4. Traffic Shaping for Workload Classification, Lucid Computing (2026). Original
5. The Tray as a Bandwidth Boundary, Amodo Design (2026). Original
6. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). Original
7. PAL*M: Property Attestation for Large Generative Models, P. Chantasantitam et al. (2026). Original
8. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
9. A primer on secure enclaves, Tinfoil (2026). Original
10. Backend infrastructure, Tinfoil (2026). Original
11. How verification works in Tinfoil, Tinfoil (2026). Original
12. modelwrap: Reproducible dm-verity read-only image of Huggingface models, Tinfoil (2026). Original
13. TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition, J. Chuang et al. (2026). Original
14. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
15. Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing, J. De Meulemeester et al. (2026). Original
16. RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP, B. Schlüter & S. Shinde (2025). Original
17. SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020), AMD (2025). Original
18. On TEEs for Privacy-Preserving Monitoring in AI Governance, Gloria Z (2026). Original
19. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). Original